mesh_recall

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so richly: it discloses auto-discovery of mcl-rag's advertised realm, the underlying answer_query call, the return shape (chunks with similarity score, source_path, chunk metadata), and that empty results are not an error. That is exactly the behavioral context an agent needs.

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?

Front-loaded with the core action and qualifier ('semantic retrieval, not keyword match'), then builds out behavior. It is longer than most definitions, but nearly every sentence adds distinct value (realm discovery, return shape, empty result meaning, invocation timing).

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?

No output schema exists, yet the return values are described in-detail, and empty-result semantics plus the auto-discovery mechanism are covered. Nothing an agent needs to call this correctly is missing.

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 both query_text and top_k are already documented by the schema. The description adds useful framing of query_text as a semantic query rather than a keyword string, but adds nothing for top_k, so the baseline 3 holds.

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?

States a specific verb (Query) and resource (mesh's shared memory / mcl-rag RAG service), and sharpens it by contrasting semantic retrieval against keyword match. It names mesh_remember as the deposit counterpart, letting an agent place it against siblings without opening any schema.

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?

Explicitly says 'Not automatic -- call this deliberately when you actually want to check shared memory' and gives a concrete trigger ('early in a session working on a repo others may have touched'). This supplies the when-to-use and the deliberate-invocation condition rather than leaving it to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.