Rechercher des actions

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, covering the safety profile well. The description adds the return format ('Liste des actions correspondantes') and the projection behavior implicitly via the fields parameter. With annotations covering the safety traits, the description adds reasonable supplemental context without contradicting 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 a compact two-part structure: a French narrative sentence followed by an Args list and Returns line. It's reasonably concise and front-loaded with the core purpose. The Args section is slightly redundant given 100% schema coverage but short enough to be non-burdensome.

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 search/read tool with strong annotations (readOnly, openWorld, idempotent) and full schema coverage, the description is mostly adequate. However, given no output schema, it could clarify return shape (does 'Liste des actions' include pagination metadata? are there default fields projected?) more explicitly. The description mentions the projection 'fields' param is in schema, but return defaults are vague.

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 8 parameters have descriptions in the schema itself. The tool description restates parameter intent (keywords for search terms, ID filters for entity linkage, page/pageSize for pagination) but adds minimal new meaning beyond what the schema already provides. The description's restatement is helpful for a quick scan but doesn't substantially exceed 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 states the verb (recherche) and resource (actions), and lists the entity types (calls, emails, meetings, notes) which adds specificity. However, it doesn't strongly differentiate from siblings like boond_actions_get or entity-specific action searches (boond_candidates_actions, boond_resources_actions, boond_contacts_actions, boond_companies_actions) which also search actions within entity contexts.

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 lists optional filter parameters indicating when to use them (to filter by entity). However, it doesn't distinguish when to use this global search vs the entity-scoped action search tools (candidates_actions, resources_actions, etc.), nor when boond_actions_get would be more appropriate for retrieving a specific action.

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