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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, but the description adds hard operational facts the annotations cannot convey: single SELECT statement, 500-row cap, 5-second limit, and no file or network access. Those constraints directly shape how an agent must phrase queries and handle results.

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 capability, then the limits, then the usage advice in three compact clauses. No redundant restatement of the name or title, and every clause carries actionable 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?

With an output schema present, return values need no explanation, and the description covers dialect, limits and isolation. The one gap is discoverability: it says 'las tablas del mirror' without indicating that list_datasets or describe_dataset reveal the available tables and columns, which an agent needs before writing valid SQL.

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 100% and the single parameter is already documented as 'una única consulta SELECT en dialecto DuckDB', so the baseline is 3. The description earns an extra point by adding a data-level detail absent from the schema: period columns are stored as text in 'YYYYMM' form, which prevents a common type-mismatch error.

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: read-only SQL (DuckDB) over mirror tables. That is unmistakably different from the domain-specific siblings such as inflation_series or labor_market. It stops short of a 5 because it never explicitly frames itself as the generic escape hatch alongside list_datasets/describe_dataset.

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 concrete usage direction: aggregate and filter in SQL rather than pulling raw rows, and notes periods are text ('202609'). This tells the agent how to use the tool well. It offers no explicit when-not or routing to the 16 domain siblings, which would be the natural alternative for common indicators.

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