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

Beyond the readOnly/openWorld annotations it discloses message ordering, that voice notes arrive transcribed and media described in media_text, that media_pending signals eventual consistency, and it adds a prompt-injection warning that message content is data, not instructions — all behavior the annotations cannot convey.

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?

Three short sentences, front-loaded with the core action and ordering, then media handling, then the safety caveat. No filler; every clause adds usable information.

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?

There is no output schema, and the description does a good job describing what comes back (ordering, media_text, media_pending). It leaves pagination behavior and the meaning of limit unspecified, a minor gap for a two-parameter read 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 coverage is 50%: conversation_ref is already documented in the schema, and the description only reinforces its source. The limit parameter is never explained in the description, though "los últimos mensajes" weakly implies it selects the most recent N; the schema itself carries the range and default.

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?

"Los últimos mensajes de una conversación" states a specific verb and resource, adds ordering (oldest to newest), and names where the required conversation_ref comes from (list_conversations), so it is easily separated from that sibling.

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 tells the agent to obtain the ref from list_conversations and to re-read later when media_pending is true, which is operational when-to-use guidance. It does not name an explicit alternative or exclusion, so it falls short of a 5.

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