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

Adds two non-obvious traits beyond the readOnlyHint annotation: reading does not mark the message as read (and names the tool that does), and the message body is human-authored data, not agent instructions — a substantive prompt-injection warning. Neither is derivable from the schema or 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?

Front-loads what the tool does, then the not-marking-as-read behavior, then the untrusted-content caveat — a sensible ordering. The injection warning is wordy ('lo presenta como lo que es...') but the redundancy reinforces a safety-critical point rather than wasting space.

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 one-parameter read with no output schema, the description covers what the caller needs: how to obtain the id, that no read-state side effect occurs, and the nature of the returned content. The exact shape of the returned message beyond `note` is left implicit, a minor gap.

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 0% for the single id parameter, but the description states its origin ('el que da list_messages'), which is exactly the missing semantic the schema omits. No format or validation detail, but the sourcing guidance is the most useful thing to add here.

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?

Starts with a specific verb and resource ('Lee un mensaje directo... por su id'), and clarifies the 'entero' scope versus the list view. Sibling differentiation is present but indirect — it references list_messages and mark_message_read by function rather than naming them as alternatives.

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?

Gives an explicit use condition (read one full message when you have its id from list_messages) and redirects the marking-read use case to mark_message_read. No exclusions or preconditions beyond that, but the routing is clear enough.

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