Rechercher des todolists

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

Annotations are rich: readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=true. The description adds the pagination behavior and the note that unknown field names are 'ignorés' silently, which is a valuable behavioral disclosure beyond the annotations. It also clarifies that absent fields defaults to a standard summary, providing useful transparency.

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 — two short sentences plus an Args block. It's well-structured and front-loaded with the main purpose before parameter details. The only minor waste is the duplicate documentation of page/pageSize defaults that already exist in the schema, but this is small and does not harm readability.

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 tool with rich annotations (read-only, idempotent, non-destructive, open-world) and a full output schema, the description is largely complete. It covers purpose, keyword semantics, pagination, and the projection/fields behavior. It could add a note about result count or total-pages, but the output schema and openWorldHint annotation compensate for most gaps. This is appropriately complete for a read-only, well-annotated search tool.

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 4 parameters (page, pageSize, keywords, fields) are fully documented in the schema itself. The description restates keywords and pagination params but adds marginal value. The most interesting addition is the 'fields' projection semantics (absent = résumé standard, noms inconnus ignorés), which is also echoed in the schema. With full schema coverage, baseline of 3 is appropriate.

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 todolists dans BoondManager par mots-clés avec pagination' — a specific verb (search) with a specific resource (todolists) and scoping (by keywords with pagination). It clearly distinguishes from sibling tools like boond_todolists_get (which retrieves a single record) and other *_search tools that operate on different entities (companies, candidates, contacts).

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 establishes clear context for use (searching todolists by keywords with pagination). However, it does not explicitly state when NOT to use it or name alternatives — e.g., when to prefer boond_todolists_get for a single known entity. The keyword scope (nom, email, compétences) gives some usage hint but no explicit exclusion or alternative guidance.

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