Rechercher des calendriers

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds the pagination behavior and the 'fields' projection mechanism (noting unknown field names are ignored, in the schema). It doesn't describe return volume limits or rate limiting, but beyond annotations the tool is read-only search — the description adds modest value but doesn't significantly enrich behavioral context.

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 French description is concise and front-loaded with the verb+resource, followed by a clean Args block and a Returns statement. Well structured with useful defaults noted (page: 1, pageSize: 20). Minor redundancy: the description's pageSize default (20) conflicts with the schema's default (30), and Args paragraph partially duplicates schema info — but overall efficient and readable.

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?

The tool is a straightforward read-only search with an output schema present, so return values are already documented. The description covers keywords, pagination defaults, and return summary. The 'fields' projection is described only in the schema, which is acceptable. A minor default-value inconsistency (pageSize 20 vs 30) between description and schema reduces completeness slightly.

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 coverage is 100%, so the description need not repeat parameter details. The description does summarize the keywords, page, pageSize parameters correctly and adds context for keywords (what can be searched — nom, email, compétences). However, the 'fields' projection parameter is not mentioned in the description beyond the schema. Baseline 3 is appropriate given full schema coverage.

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 'Recherche des calendriers dans BoondManager par mots-clés avec pagination' — a specific verb (rechercher), resource (calendriers), and clear scope (keyword-based, paginated). It distinguishes from siblings like boond_calendars_get (retrieval by ID) and other *_search tools by resource type.

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 states it searches calendars by keywords with pagination, giving clear context for its intended use. However, it doesn't explicitly say when to use this vs the sibling boond_calendars_get, nor does it provide any exclusions or alternative tools. The keyword examples (nom, email, compétences) hint at usage but don't contrast with alternatives.

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