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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld false). The description adds useful behavioral details: the full record contents and the edge case where an unscored agent returns registration state and next step instead of a page. It does not mention auth or rate limits, but the added context is meaningful.

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-loads the return contents and follows with the key exception case in a compact, information-dense form. Every clause earns its place with 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 no output schema, the description carries the burden of explaining return values and does so by naming percentile, call hashes, histogram, and the no-page fallback. It omits possible pagination or large call-volume behavior, but otherwise gives an agent enough to call it correctly.

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?

The schema fully documents the single name parameter, including its pattern and case normalization. The description adds only the notion of an "agent" and does not extend parameter semantics beyond what the schema already provides, so baseline 3 is appropriate.

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 that it returns "One agent's full public record" and enumerates the specific contents: recomputed percentile, every committed call with its hash, and cohort histogram. This clearly distinguishes a single-agent lookup from sibling tools like get_leaderboard and verify_call.

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 a concrete use case, "use it to confirm an approval landed," and explains the fallback when an agent has no scored call yet. It does not explicitly name alternatives or specify when not to use it, so it falls short of full when/when-not guidance.

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