Rechercher des avantages

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, fully covering the safety profile for a search operation. The description adds the concrete example types of benefits (tickets restaurant, mutuelle, véhicule...) and notes the optional resource filter and pagination parameters, contributing meaningful behavioral context beyond the annotations.

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?

The description is compact, listing the purpose line then a concise Args breakdown. It's reasonably front-loaded with the purpose statement and example benefit types. Minor redundancy with the schema (repeating keywords/resourceId/page), but the example benefits and the note about field projection default behavior add value. Could trim slightly but is well-structured.

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 read-only filtered search tool with 100% schema coverage, full annotations, and no output schema, the description covers the key aspects: what is searched, example content types, filter options, and pagination. The 'fields' projection behavior (default summary, unknown names ignored) is partially covered by the schema. It's adequately complete for this tool class, though it could name the sibling boond_advantages_get for disambiguation.

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 all 5 parameters are documented in the schema itself (keywords, resourceId, page, pageSize, fields). The description mentions keywords, resourceId, and pagination briefly but adds nothing beyond the schema notes. The description does usefully echo the core filter parameters, but it doesn't provide example formats or value constraints beyond what the schema already gives. Baseline 3 is appropriate.

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 clearly states it searches for 'avantages' (benefits like meal tickets, insurance, vehicles, bonuses) in BoondManager with an optional resource filter. The verb+resource+scope is specific and distinguishes from boond_advantages_get (which is a detail/get sibling). However, it doesn't explicitly contrast with the siblings, though the 'search' vs 'get' naming pattern is self-evident.

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 implies usage context (search for advantages, optionally filtered by resource) but provides no explicit when-to-use vs alternatives guidance. It doesn't mention boond_resources_advantages as an alternative or clarify when to choose this search tool vs the get-by-ID counterpart. The optional filter is noted, which is helpful context.

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