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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the closing 'Lecture seule' is largely redundant, though it confirms intent. The one genuine addition is that pairing data_room_id with question yields a cited answer ('réponse citée'), which tells the agent what behavior to expect from that mode; nothing is said about pagination, result limits, or what happens with a stale cursor.

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 compact sentences, front-loaded with the scope then the exclusion, with no filler. The trailing 'Lecture seule' is the only near-waste, restating the readOnlyHint annotation.

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, rich annotations and 71% schema coverage, the definition covers what is needed to route and call the tool. The dual-purpose nature (account listing vs. Q&A over a data room) is signalled but under-explained for a 7-parameter, zero-required-parameter tool.

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 71%, so most parameters are already documented in the schema (type and theme even carry enums). The description's only semantic contribution is the pairing rule for data_room_id + question and the cited-answer outcome, which the truncated schema hint alone would not make clear; it says nothing about projet, curseur or limite beyond the schema.

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 names the specific resource ('les projets, analyses, BP, rapports et exports enregistrés par l'utilisateur dans son compte') and immediately states what the tool is NOT ('Ne recense PAS les projets urbains ni les ZAC'), naming toise_contraintes and toise_permis as the correct destinations. An agent can distinguish this from the sibling tools 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?

Explicit negative guidance with named alternatives ('voir toise_contraintes (ZAC/PUP) et toise_permis') and an implicit positive condition (saved items in the user's own account). It also hints at a second mode via 'data_room_id + question', but does not state when that mode should be chosen over plain listing.

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