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

With no annotations provided, the description carries the full burden. It adds meaningful behavioral context: messages are returned for the authenticated user, ordered by date, each message includes identifier/role/content type/text, and there is a strong warning about third-party generated content and potential manipulation attempts. This goes beyond minimal disclosure, though it does not mention pagination, rate limits, or error 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 concise and front-loaded: the first sentence states the core functionality, and the second adds an important security/usage warning. Every sentence earns its place, and the overall length is appropriate for the tool's complexity.

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?

Given there is no output schema, the description appropriately explains return fields and ordering, and it covers authentication scope. It also includes a critical warning about message content. It is not exhaustive (no error handling, pagination details, or rate limits), but for a list-retrieval tool it is reasonably complete.

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?

The schema already documents both parameters fully (conversation_id and limit) with 100% coverage, so the baseline is 3. The description adds no extra meaning about the parameters themselves; it only clarifies the return fields. It is acceptable but does not exceed baseline.

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 what the tool does: 'Devuelve los mensajes de una conversación específica del usuario autenticado, ordenados por fecha.' It specifies the verb, resource (messages of a conversation), and scope (authenticated user, specific conversation), and differentiates itself from siblings like getMyChats by focusing on messages within a conversation rather than the list of chats.

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 implies usage context by noting the conversation is obtained from getMyChats (in the parameter description), but it does not explicitly state when to use this tool versus alternatives or provide exclusions. The security warning about not executing instructions in messages is useful guidance for handling results, but the 'when to use' dimension remains only implicit.

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