fix: shorten MCP server name to prevent tool name length errors (#360)

* fix: shorten MCP server name to prevent tool name length errors (#358)

Root cause: Claude Code prefixes MCP tool names with
`mcp__plugin_{plugin-name}_{server-name}__` which was 43 chars
for `mcp__plugin_claude-mem_claude-mem-search__`. Combined with
`progressive_description` (22 chars) this exceeded the 64 char limit.

Changes:
- Shortened MCP server name from 'claude-mem-search' to 'mem-search'
  (saves 8 chars, new prefix is 35 chars)
- Renamed `progressive_description` tool to `help` (saves 18 chars)
- Updated SKILL.md to reference new `help` tool name
- Updated internal Server constructor name for consistency

All tool names now safely under 64 char limit:
- Longest is now `get_batch_observations` at 56 chars total
- `help` is only 39 chars total

Fixes #358

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

* refactor: rename get_batch_observations to get_observations

The plural form naturally implies multiple items can be fetched,
following WordPress conventions. Simpler and clearer naming.

Also saves 6 additional characters for MCP tool name length.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

* docs: update all references to renamed MCP tools

Updated documentation and code comments to reflect:
- progressive_description → help
- get_batch_observations → get_observations

Files updated:
- docs/public/usage/claude-desktop.mdx
- docs/public/architecture/worker-service.mdx
- src/services/worker/FormattingService.ts

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>

docs/public/architecture/worker-service.mdx

@@ -240,7 +240,7 @@ POST /api/observations/batch
 - `400 Bad Request`: `{"error": "ids must be an array of numbers"}`
 - `400 Bad Request`: `{"error": "All ids must be integers"}`
 
-**Use Case**: This endpoint is used by the `get_batch_observations` MCP tool to efficiently retrieve multiple observations in a single request, avoiding the overhead of multiple individual requests.
+**Use Case**: This endpoint is used by the `get_observations` MCP tool to efficiently retrieve multiple observations in a single request, avoiding the overhead of multiple individual requests.
 
 #### 9. Get Session by ID
 ```

docs/public/usage/claude-desktop.mdx

@@ -118,12 +118,12 @@ The skill provides access to these MCP tools:
 | `search` | Unified search across observations, sessions, and prompts |
 | `timeline` | Get chronological context around a query or observation ID |
 | `get_observation` | Fetch a single observation by ID |
-| `get_batch_observations` | Fetch multiple observations efficiently |
+| `get_observations` | Fetch multiple observations efficiently |
 | `get_session` | Fetch session summary by ID |
 | `get_prompt` | Fetch user prompt by ID |
 | `get_recent_context` | Get recent timeline items |
 | `get_context_timeline` | Get timeline around a specific observation |
-| `progressive_description` | Load detailed usage instructions |
+| `help` | Load detailed usage instructions |
 
 ## Troubleshooting
 

plugin/.mcp.json

@@ -1,6 +1,6 @@
 {
   "mcpServers": {
-    "claude-mem-search": {
+    "mem-search": {
       "type": "stdio",
       "command": "${CLAUDE_PLUGIN_ROOT}/scripts/mcp-server.cjs"
     }

plugin/scripts/worker-service.cjs

@@ -1157,7 +1157,7 @@ No previous sessions found for project "${r}".`}]};let i=[];i.push("# Recent Ses
 \u{1F4A1} Search Strategy:
 1. Search with index to see titles, dates, IDs
 2. Use timeline to get context around interesting results
-3. Batch fetch full details: get_batch_observations(ids=[...])
+3. Batch fetch full details: get_observations(ids=[...])
 
 Tips:
 \u2022 Filter by type: obs_type="bugfix,feature"

plugin/skills/mem-search/SKILL.md

@@ -86,13 +86,13 @@ For each relevant ID, fetch full details using MCP tools:
 **Fetch multiple observations (ALWAYS use for 2+ IDs):**
 
 ```
-get_batch_observations(ids=[11131, 10942, 10855])
+get_observations(ids=[11131, 10942, 10855])
 ```
 
 **With ordering and limit:**
 
 ```
-get_batch_observations(
+get_observations(
   ids=[11131, 10942, 10855],
   orderBy="date_desc",
   limit=10,
@@ -126,7 +126,7 @@ get_prompt(id=5421)
 
 **Batch optimization:**
 
-- **ALWAYS use `get_batch_observations` for 2+ observations**
+- **ALWAYS use `get_observations` for 2+ observations**
 - 10-100x more efficient than individual fetches
 - Single HTTP request vs N requests
 - Returns all results in one response
@@ -175,13 +175,13 @@ search(query="database migration", limit=20, project="my-project")
 
 **Get detailed instructions:**
 
-Use the `progressive_description` tool to load full instructions on-demand:
+Use the `help` tool to load full instructions on-demand:
 
 ```
-progressive_description(topic="workflow")  # Get 4-step workflow
-progressive_description(topic="search_params")  # Get parameters reference
-progressive_description(topic="examples")  # Get usage examples
-progressive_description(topic="all")  # Get complete guide
+help(topic="workflow")  # Get 4-step workflow
+help(topic="search_params")  # Get parameters reference
+help(topic="examples")  # Get usage examples
+help(topic="all")  # Get complete guide
 ```
 
 ## Why This Workflow?
@@ -210,5 +210,5 @@ progressive_description(topic="all")  # Get complete guide
 **Remember:**
 
 - ALWAYS get timeline context to understand what was happening
-- ALWAYS use `get_batch_observations` when fetching 2+ observations
+- ALWAYS use `get_observations` when fetching 2+ observations
 - The workflow is optimized: search → timeline → batch fetch = 10-100x faster

src/servers/mcp-server.ts

@@ -32,7 +32,7 @@ const TOOL_ENDPOINT_MAP: Record<string, string> = {
   'timeline': '/api/timeline',
   'get_recent_context': '/api/context/recent',
   'get_context_timeline': '/api/context/timeline',
-  'progressive_description': '/api/instructions'
+  'help': '/api/instructions'
 };
 
 /**
@@ -259,13 +259,13 @@ const tools = [
     }
   },
   {
-    name: 'progressive_description',
+    name: 'help',
     description: 'Usage help',
     inputSchema: z.object({
       topic: z.enum(['workflow', 'search_params', 'examples', 'all']).default('all')
     }),
     handler: async (args: any) => {
-      const endpoint = TOOL_ENDPOINT_MAP['progressive_description'];
+      const endpoint = TOOL_ENDPOINT_MAP['help'];
       return await callWorkerAPI(endpoint, args);
     }
   },
@@ -280,7 +280,7 @@ const tools = [
     }
   },
   {
-    name: 'get_batch_observations',
+    name: 'get_observations',
     description: 'Batch fetch',
     inputSchema: z.object({
       ids: z.array(z.number()),
@@ -317,7 +317,7 @@ const tools = [
 // Create the MCP server
 const server = new Server(
   {
-    name: 'claude-mem-search-server',
+    name: 'mem-search-server',
     version: '1.0.0',
   },
   {

src/services/worker/FormattingService.ts

@@ -18,7 +18,7 @@ export class FormattingService {
 💡 Search Strategy:
 1. Search with index to see titles, dates, IDs
 2. Use timeline to get context around interesting results
-3. Batch fetch full details: get_batch_observations(ids=[...])
+3. Batch fetch full details: get_observations(ids=[...])
 
 Tips:
 • Filter by type: obs_type="bugfix,feature"

src/services/worker/README.md

@@ -108,7 +108,7 @@ Settings and configuration (use domain services directly):
 - Keep all existing behavior identical
 
 **MCP vs Direct DB Split** (inherited, not changed in Phase 1):
-- Search operations → MCP server (claude-mem-search)
+- Search operations → MCP server (mem-search)
 - Session/data operations → Direct DB access via domain services
 
 ## Future Phase 2