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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint false, so the description is not solely responsible for safety. It adds behavioral context by specifying the output format (CSV), the grouping/sorting logic, the input size limit, and the monetary cost per call. It does not contradict 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?

The entire description is a single, front-loaded sentence that states the action, input, output, and a key transformation, followed by a separate pricing note. No filler or redundant content.

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 tool with one input parameter and no output schema, the description covers the essential behavior: expected input type, output format (CSV), and processing logic. It lacks details on CSV columns and error handling, but these are minor for a tool this simple, given the annotations also cover safety.

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 describes 'data' as 'JSON de entrada (máx. 1 MB)'. The description elaborates that this JSON is a usage export from an LLM API, adding semantic meaning that the schema alone lacks. With 100% schema coverage, this is a meaningful bonus, though it still does not specify the JSON structure.

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 the tool receives a JSON export of LLM API usage and returns a CSV of requests that missed cache, grouped by prefix and sorted by cost. This distinguishes it from all sibling tools, which appear unrelated (e.g., 'leer-pagina-markdown', 'indicador-eurostat').

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 when to use: when a user has a JSON usage export and wants to identify uncached prompts. However, it does not explicitly state when NOT to use it or compare with alternative tools, so it leaves the agent to infer the appropriate context.

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