Search

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

readOnlyHint=true already covers the safety profile. Beyond that, the description discloses the retrieval mechanism (hybrid dense+sparse with reranking) and the shape of the result (short excerpts with doc_id, titre, projet, score), which genuinely helps an agent reason about result quality and next steps.

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?

Three tight sentences: purpose and mechanism first, then the call-timing guidance, then the return shape and the routing hint. No filler, and the most decision-relevant information is front-loaded.

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?

With an output schema present, return values need not be spelled out, and the brief mention of excerpt fields is a bonus. Combined with the retrieval mechanism and the `get` handoff, an agent has enough to call it correctly; only filtering behavior across the sibling tools is left implicit.

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 description coverage is 100%, so `k`, `tags`, `project` and `query` are all documented in the input schema itself. The description adds no extra semantics about these parameters, so the baseline 3 applies.

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+resource with mechanism: hybrid (dense + sparse, reranking) search over Denis's memory, and explicitly distinguishes itself from the sibling `get` (excerpts vs. full document). An agent can tell what it is without opening the 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?

"À appeler avant de répondre sur ses projets, décisions ou notes" gives a clear trigger context, and it names `get` as the alternative for reading a whole document. However, it gives no exclusions — e.g., nothing says to use `list_docs` or `projects` for enumeration instead.

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