Rechercher des business units

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds the pagination behavior and return summary. It doesn't detail edge cases like empty results, or behavior when keywords are absent (returns all?), but with strong annotations covering the safety profile, this is acceptable.

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 at 4 sentences and front-loads the purpose. The Args section is somewhat redundant with the schema (which documents all 4 params at 100% coverage), but it's brief and doesn't waste many words. No fluff, though padding with schema-duplicated parameter details slightly reduces efficiency.

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?

Has an output schema, so return format needs no description. The 'fields' projection explanation adds real value for customization. For a filtered search tool with good annotations, a readOnly, idempotent operation, this is reasonably complete. Slight gap: no mention of max pageSize mismatch (schema says 500, description says 100) and no guidance on pagination strategy for large result sets.

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 the schema documents all parameters. The description adds useful context beyond the schema: it explains the 'fields' projection concept (standard summary vs custom attributes, unknown names ignored) which is unique and genuinely helps the agent. It also clarifies that keywords cover name/email/skills, adding search scope semantics not in the 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 description clearly states it searches ('Recherche') business units in BoondManager by keywords with pagination, and specifies the return type (list of business units with ID, name, main details). It distinguishes from sibling boond_business_units_get (which fetches a single unit) but doesn't explicitly name the alternative search tools like boond_companies_search or boond_resources_search that could be confused.

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 (keyword search with pagination) and the readOnly/soft hints suggest non-destructive selection. However, there's no explicit when-to-use vs alternatives, no exclusion criteria, and it doesn't clarify the distinction between searching business units vs companies or resources vs candidates, despite the large sibling set.

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