Rechercher des livraisons / CRA

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 well covered. The description adds the return type ('Liste des livraisons correspondantes') and filter scope, but doesn't add deeper behavior details like default ordering, field projection limits, or how openWorldHint affects results. With strong annotations covering safety, the description adds modest additional 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 description is reasonably compact, with a clear opening sentence, then an Args list and Returns line. It's efficient with two short sections. The Args list is slightly redundant with the schema but kept brief. No wasted verbiage.

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?

This is a search tool with 8 parameters (all optional), no output schema, and strong annotations. The description covers the filter dimensions and return type adequately. However, it doesn't explain pagination default behavior beyond the schema defaults, doesn't note that dates are exclusive/inclusive, and doesn't clarify relationship between companyId/projectId filtering since both are optional. For a list-search tool with good annotations, it's adequate but not rich.

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% (all 8 parameters have descriptions). The description's 'Args' section largely restates what's already in the schema (keywords, projectId, companyId, startDate/endDate, page/pageSize). It adds the date format '(YYYY-MM-DD)' which is also in the schema. The 'fields' parameter projection behavior is already well documented in the schema ('Projection: attributs à afficher... Noms inconnus ignorés'). No significant added value beyond 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 the verb ('Recherche des livraisons'), the resource (deliveries/activity reports in BoondManager), and the key filters (project, company, period). It distinguishes from sibling tools like boond_deliveries_get (single retrieval) and boond_deliveries_create (mutation), and the title reinforces the 'Rechercher des livraisons / CRA' purpose.

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 it is a search tool for deliveries with filters, which is clear from the description. However, it does not explicitly state when to use this tool versus alternatives (e.g., boond_deliveries_get for retrieving a single delivery, or timesheets/expenses/absences search for other CRA types). No exclusions or 'use X instead' guidance is provided.

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