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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, covering the safety profile. The description adds modest behavioral context (the catalog surfaces warnings and the last complete production month, and expands to columns when 'tablas' is passed), but much of that overlaps the output schema, so it adds limited value beyond structured fields.

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?

Very compact and front-loaded — 'Start here' leads, followed by a terse enumeration of returned fields and a usage example. The field list is telegraphic but every clause carries information, and there is no filler.

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, the description needn't explain return values, and annotations cover the safety profile; the description supplies the orientation ('start here'), the array semantics, and a call example. The only real gap is that 'max_rows' is never explained, which is a minor omission for a 2-param discovery 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%: 'tablas' is documented ('Tables or views whose columns you need') while 'max_rows' is completely undocumented. The description adds a concrete call example ({tablas: ['pozos']}) and clarifies that passing tablas also returns columns, which partly compensates, but 'max_rows' remains unexplained in both schema and description.

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 makes clear this is the catalog/discovery entry point that enumerates every table and view with metadata (description, period, rows, warnings, recommended tool), and 'Start here' plus the title 'Data catalog' distinguish it from the query_* siblings. It lacks an explicit verb ("describe"/"list"), relying on the field enumeration to convey purpose, but the intent is unambiguous.

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?

'Start here' is a direct, front-loaded usage directive telling the agent to call this before other tools, and 'tool to use' implies the catalog routes the agent to the query_* siblings. It gives clear when-to-use context but names no explicit alternatives or when-not conditions.

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