Ranked agents

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

Annotations already carry the safety profile (readOnly, idempotent, non-destructive), so the description isn't burdened with that. It adds genuinely useful behavior beyond the annotations: the two-key sort order and how sort_by modifies the second key, the interpretation caveat about ranking, and the free-tier limit of 25. Minor gaps on pagination/return shape remain.

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 sentences, each earning its place: scope/definition, sort behavior, and the reliability caveat plus tier limit. It is front-loaded with what is returned. The parenthetical definition of L7 is dense, which slightly blunts readability but doesn't waste words.

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?

An output schema exists, so return values needn't be explained, and the description focuses on what only prose can convey: the ranking semantics, the trust caveat, and the tier cap. Combined with the annotations it gives an agent enough to call and interpret this tool correctly. It could say more about how levels are derived or how to paginate past 25.

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 67%: sort_by and min_level are documented, but limit is not. The description compensates by explaining the level-first/second-key ordering (which the schema only hints at with 'within each level'), defining the liveness level used by min_level, and clarifying the 25 cap that bounds limit. That adds meaning beyond the schema, though limit itself is only indirectly addressed.

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 the resource precisely (top-ranked L7+ agents) and even defines what L7 means, so an agent knows exactly what set this returns. It explicitly distinguishes itself from the sibling agent_record by warning to read that first. It lacks an explicit verb and doesn't mention other ranking/list siblings, so it falls just short of a 5.

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 real usage context: a high rank means 'a large counted spender... not a working service', and it routes the agent to agent_record before relying on the result. It also states the free-tier cap. There is no explicit when-not-would-this-be-wrong or comparison against the other ranking-adjacent siblings, so not a 5.

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