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

Beyond the readOnlyHint and idempotentHint annotations, the description explains the search scope (1-to-1 chats ranked by recency, plus contacts) and the three return states (resolved, ambiguous, not_found) with specific follow-up actions for each. This adds significant behavioral context not available in annotations.

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?

Every sentence earns its place: first sentence defines purpose and scoping, second explains return behavior, third provides examples, fourth gives a caution. The information is dense but logically ordered and free of filler.

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 no output schema, the description fully explains the return values (resolved, ambiguous, not_found) and their handling, the search ranking, and even the caveat about account_id. For a 3-parameter tool with no output schema, this is complete and actionable.

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 schema already explains name, provider, and account_id. The description reinforces that name can be a nickname or phone number (already in schema) and warns against passing a name as an ID, but it adds no new parameter-level meaning beyond what the structured schema provides.

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 states a specific verb ('Turn a person's name... into the exact recipient') and resource (WhatsApp/Instagram/Telegram recipient), and clearly distinguishes it from siblings like messaging_find_chat_by_user by emphasizing resolution before sending. It even includes concrete example queries and a warning against misuse.

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?

It gives explicit when-to-use examples ('send a WhatsApp to Julien', 'reply to Marie on Instagram', 'message +33 6…') and states it should be used BEFORE sending. It also warns against passing a name as chat_id or user_id, effectively directing the agent away from incorrect usage patterns.

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