annuaire_rechercher

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: results are permission-filtered to contacts the user may reach, and the payload is identifiers intended to feed a messaging call. It still omits pagination or result-size behavior, keeping it short of a 5.

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?

Two sentences, front-loaded with the action verb, and both carry weight — one defines scope, the other defines the return intent. The parenthetical contact list is a slight expansion but usefully bounds the scope rather than padding.

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 single-parameter, read-only lookup with no output schema, the description covers purpose, scope, and what comes back (identifiers for messaging) plus the permission boundary. Nothing critical for correct invocation is missing, though pagination/output shape is left implicit.

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 single 'recherche' parameter is fully documented in the schema (name, class, function, empty = all). The description adds no query-syntax or matching details beyond what the schema already provides, so the baseline 3 applies.

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?

States a specific verb (Recherche) plus resource (annuaire) and narrows scope to people and groups the caller is authorized to contact, with examples of contact types. It also names the outcome (identifiers for sending a message), which separates it from siblings like annuaire_fiche and the messagerie_* family.

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?

Usage context is implied: the reader infers this is the lookup step before composing a message. However, there is no explicit when-to-use/when-not guidance and no mention of annuaire_fiche as the detail-lookup alternative, so routing between the two directory tools must be guessed.

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