Rebuild the search index from Markdown files. Optionally rescan a codebase to refresh symbol lookup and code map note.
Rebuild the search index from the Markdown files. Always safe: the index is a cache and deleting it loses nothing. If path is given, also rescan that codebase into the symbol index and refresh its code map note.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | codebase root to scan | |
| scope | No | scope name for the scan |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It honestly discloses that the index is a cache, that deleting it loses nothing, and that path triggers additional rescan/refresh actions. This directly addresses potential destructive concerns without relying on annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with zero filler. The main action and safety guarantee are front-loaded, followed by the conditional behavior. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema and no annotations, the description explains core behavior but omits what the tool returns and how `scope` affects the operation. It also lacks any guidance on when to use this over siblings. Adequate but has clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds meaning beyond the schema by specifying that `path` triggers a codebase rescan and code map refresh. It does not elaborate on `scope`, but the added context for `path` elevates the score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the operation with specific verbs and resources: 'Rebuild the search index from the Markdown files' and 'rescan that codebase into the symbol index and refresh its code map note.' This distinguishes it from sibling tools like agtmem_search (search) and agtmem_read/write (content access).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives context about safety ('Always safe') and conditional behavior ('If path is given'), but it does not explicitly say when to use this tool versus alternatives like agtmem_search or agtmem_find. Usage is implied rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.