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

Adds concrete effects beyond the annotations: unread flag clears, the bell counter decreases, the call returns how many messages changed, and read=false reverses the operation. This is consistent with idempotentHint=true and destructiveHint=false. It does not cover partial-failure behavior when some ids are invalid.

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-loaded with the action and target, then effects, then the reverse-mode caveat and scope. Dense but every clause carries information; slight chaining makes it a single long run-on sentence.

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 2-parameter mutation with no output schema, it covers the state change, the return value ('cuántos cambió'), the reverse mode, and the ownership scope. Only edge-case behavior (invalid/foreign ids, batching limits) is left unstated.

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%, so the description must carry the semantics: it identifies `ids` as direct-message ids from list_messages and defines `read=false` as unmarking, which is the non-obvious meaning of that boolean. Minor schema facts (maxItems 100, minItems 1) remain only in the schema.

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 and resource ('Marca como leídos tus mensajes directos') and ties the `ids` input to its source ('los de list_messages'), which distinguishes it from the read-only list sibling. An agent knows exactly what state change this produces.

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?

Explains where the ids come from (list_messages) and documents the reverse-mode alternative via read=false, plus the ownership constraint ('Solo toca los tuyos'). It does not spell out exclusions or when not to use it, but no sibling competes for this action.

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