Reporting projets

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description does not need to repeat safety. It adds useful behavioral context: without perimeter filters the report covers the entire authorized scope, and states/types must come from boond_application_dictionary. This goes beyond annotations, though it does not mention caching or pagination behavior.

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 short, front-loaded with purpose, and uses labeled lines ('Filtres clés', 'Returns'). It is easy to scan. The only flaw is the phantom 'period' reference, which slightly detracts from precision, but overall it is concise and 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?

With 22 parameters and no output schema, the description covers the main behavioral rules (default perimeter, dictionary IDs) but offers only a generic 'Données de reporting' for return values. It does not explain the structure of the response or how filters combine by default (OR vs AND), which is left to the schema. Given the richness of the schema, this is adequate but not comprehensive.

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 descriptions cover 100% of parameters, giving a baseline of 3. The description groups filters (perimeter, period, projectTypes, etc.) which adds some structure, but it incorrectly mentions a 'period' parameter that does not exist in the schema (only startDate/endDate and periodDynamic are present). This misleading reference outweighs the organizational benefit.

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 opens with 'Reporting des projets (CA, marge, rentabilité...)' which is a specific verb+resource pairing that clearly distinguishes this tool from sibling reporting tools (boond_reporting_companies, boond_reporting_resources, boond_reporting_synthesis). It also outlines key filters, making the tool's purpose unmistakable.

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 provides clear context for when to use this tool: project reporting with filters for perimeter, period, project types/states, resources, etc. It also explicitly notes the default scope behavior ('Sans filtre de périmètre, le reporting porte sur tout le périmètre autorisé'). However, it does not explicitly name alternative tools for when not to use this one, e.g., boond_reporting_companies for company-level reporting.

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