search_messages

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful search semantics beyond annotations: AND logic across all words, accent and case insensitivity, and result ordering (most recent first). It stops short of describing pagination or result shape.

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 tight sentences, zero waste, with the core purpose and the query-matching rules front-loaded. Every clause earns its place.

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?

An output schema exists so return values need no explanation, and the query semantics are well covered. However, for an 8-parameter tool, the description is silent on the time-range (since/until), account, and pagination (offset) parameters, leaving the agent dependent on partial schema descriptions.

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 coverage is 50%, so half the parameters (since, until, account, offset) are undocumented everywhere. The description reinforces the query semantics (all words required, accent/case-insensitive) and the searchable fields, but adds nothing for the undocumented time-range and account parameters, so it does not fully compensate for the gap.

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+resource ('Recherche plein texte dans les messages') and clarifies scope by naming what fields are searched (text, captions, filenames) and ordering (most recent first). It is distinguishable from siblings like list_messages or get_message_context, though it does not name them explicitly.

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 conveys implied usage (find messages by text) but gives no when-to-use guidance against alternatives such as list_messages or get_message_context, and no exclusions or prerequisites. Nothing tells the agent under which conditions this is the right choice.

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