Rechercher des brevets

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

annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that the search spans four INPI collections and that criteria are AND-combined, which is useful behavior. It says nothing about result shape, pagination ceilings, or cost/latency of broad queries (position max 500, taille max 100 only live in the schema).

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, front-loaded with the scope statement before the field list; the AND-combination rule is placed last where it belongs. The field enumeration is long but earns its place as a quick scan of searchable axes.

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 19-parameter, fully self-documented search schema with no output schema and no required params, the description covers collections, searchable axes and filter combination. The main residual gap is that return format and pagination behavior are left entirely to the schema, and no sibling routing is offered.

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% and each of the 19 parameters is documented in the schema (formats, defaults, SIREN pattern, wildcards, requete_avancee field codes). The description's field enumeration largely mirrors the schema, adding the CIB/CPC hint and the title/abstract scoping for keywords, but no syntax or interaction rules beyond that. 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 ('Recherche') plus the exact resources covered: FR, EP, WO patent applications and CCPs, in the INPI database. The enumeration of searchable fields further pins down scope. It does not name the sibling fiche_brevet to distinguish list-vs-detail, so it stops short of a 5.

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?

'Les critères se cumulent' tells the agent filters combine as AND, which is real usage guidance, and the field list implies which queries are possible. But there is no explicit when-to-use / when-not / alternative routing, e.g. that fiche_brevet should be used once a number is known or that an empty result should be broadened.

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