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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the description does not need to restate the safety profile. It instead adds genuinely new behavioral detail: the 50-result hard cap and the caveat that the boolean filters only keep establishments that actually confirmed the attribute, plus that langue changes returned labels and links. Return shape and pagination beyond the cap remain unstated.

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?

Purpose is front-loaded in one line, then parameters are presented as a compact key-to-meaning list with no filler. Every line adds information an agent could not get from the schema.

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 seven-parameter, zero-coverage search tool it is nearly complete: all filters, their formats and their limits are covered. The main omission is what a result entry looks like and whether to page beyond the 50-item cap, which matters with no output schema present.

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 0%, so the description carries the full burden and does so for all seven parameters: it enumerates the accepted technique values, gives arrondissement formats ("1 à 20, '11e', 75011"), names the fields mot_cle searches, defines both booleans as confirmed-only filters, caps limite at 50, and lists the six langue codes. This is a full compensation for the empty 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 opening line gives a specific verb and resource ("Recherche des imprimeurs parisiens") with an implicit geographic scope. It never distinguishes itself from near-siblings such as trouver_imprimeur_capable or lister_techniques, so an agent must guess which search entry point applies.

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 explains how to fill each filter but never says when this tool is the right choice versus the six siblings, nor what happens with no filters at all. Nothing signals when to stop browsing with this and switch to fiche_imprimeur or preparer_demande_devis.

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