Rechercher des opportunités

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description focuses on additional behavioral nuances: server-side filtering, paginated return, sorting options, perimeter filter combination (OR by default, AND with narrowPerimeter), keyword prefix semantics, and projection behavior (unknown field names ignored). This meaningfully exceeds the annotations' safety-only information.

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?

Although long, the description is extremely information-dense and well-structured: a one-sentence purpose statement followed by bolded grouped bullet points for each logical use case, then sorting and return behavior. Every sentence adds actionable value for a complex 27-parameter search tool, and the formatting makes the content easily scannable.

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?

Despite the tool's high complexity (27 optional parameters, no required ones), the description covers the key filtering patterns, sort options, pagination, and explicitly points to detail tools for follow-up. The output schema exists, so not detailing the full return shape is acceptable. The description also mentions dictionary sources for many ID-based filters, making it nearly complete for practical use.

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?

With 100% schema description coverage, the baseline is 3, but the description adds substantial semantics on top: it explains how perimeterDynamic/perimeterManagers relate to user identity, gives concrete examples for state/type filters, and details keyword prefix conventions (CSOC, CCON, CAND, etc.). This goes well beyond the one-line schema descriptions and helps an agent choose and compose parameters correctly.

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 starts with a clear, specific statement: 'Recherche des opportunités commerciales dans BoondManager avec filtres serveur' — a search action on the opportunities resource with server-side filtering. It further distinguishes itself from detail-fetching tools by explicitly directing users to boond_opportunities_get for full detail, separating it clearly from siblings.

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 provides an extensive 'Cas d'usage courants' section that maps real-world intents (my opportunities, states/types, linked entities, business fields, positionings, date ranges) to specific filter parameters and examples. It also references dictionary tools for ID lookups and explicitly says to use boond_opportunities_get for detail, giving clear when-to-use and when-not-to-use guidance.

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