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

Annotations already cover the safety profile (readOnly, idempotent, not open-world, non-destructive), and the description adds genuinely new behavioral content: the output is a descriptive ranking over two time windows, draws are random, and the results must never be used to recommend numbers. That use-policy warning is not expressible in 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?

Three front-loaded sentences: when to use, what comes back, and the caveat. Each sentence carries distinct information, and the trigger examples precede the return description so an agent can route on the first clause.

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 no output schema, the description does the work of describing the return shape (frequency overall and over 90 days, longest-absent endings), which is enough for an agent to call and interpret it. It is slightly incomplete on ordering/format of the two rankings and whether jurisdiction affects ranking composition.

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 both parameters (limit, jurisdiction) are documented in the schema, so the baseline is 3. The description hints at what is ranked ('each ending 00-99', 'overall and in the last 90 days') but adds no syntax or format detail for limit or jurisdiction beyond 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?

The description states a specific verb and resource ('Returns how often each ending (00-99) came out a la cabeza') and pins down the scope: overall, last 90 days, and longest-absent. This cleanly separates it from siblings like get_results (raw draw history) and check_number (single-number lookup).

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?

It gives explicit trigger phrasing tied to real user queries ('números más salidos', 'números más atrasados', 'qué número salió más en la Provincia'), so the agent knows when to pick it. It does not explicitly contrast with get_results or get_cabezas, which is the one remaining gap given the 'history of past results' overlap.

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