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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds behavioral details: it returns pre-sorted results and includes each source's own rank and the population it was ranked against. It also notes the metric must be 'verified' and the season is singular. These are useful, but the description does not disclose potential edge cases (e.g., empty results, default order, or how asc/desc sorting affects the ranking). Since annotations carry the core behavior, a 3 is appropriate.

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 description is two sentences, with the primary function and output details front-loaded in the first sentence and a crucial pointer to list_metrics in the second. There is zero fluff, and every phrase adds value. The structure is efficient and easy to parse for an agent.

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?

Given the tool has 6 parameters, no output schema, and 0% schema description coverage, the description leaves significant gaps. It explains the core purpose and the metric parameter's validation via list_metrics, but omits details on the remaining parameters (limit, order, position, entity_kind), their defaults, and how the output is structured beyond rank and population. An agent would struggle to call this tool correctly without additional inference or probing.

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%, meaning the description must explain parameters, but it only touches on metric indirectly ('Call list_metrics for the metric keys this accepts') and season ('one season'). It does not explain limit, order, position, entity_kind, or their valid values and defaults. The description fails to compensate for the lack of schema documentation, leaving the agent with little guidance on how to set these parameters correctly.

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 returns 'Top entities on one verified metric for one season, pre-sorted, each with the source's own rank and the population it was ranked against.' This is a specific verb-resource pair (query stat leaders) with precise details about the output (rank and population). It also implicitly differentiates from list_metrics by instructing to call it for metric keys, avoiding ambiguity. The title 'Verified stat leaders' reinforces the purpose without being tautological.

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 provides some usage context by saying 'Call list_metrics for the metric keys this accepts,' which tells the agent to use list_metrics when needing valid metric keys. However, it does not explicitly state when to use this tool versus alternatives like run_stat_query, compare_entities, or get_entity_metrics. There are no exclusions or alternative routing beyond the single list_metrics pointer, so guidance is partial.

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