audit_leaderboard

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds behavioral context by explaining that results are interpreted as per-item solved sets and that the tool computes bootstrap-based confidence intervals (via n_boot), which goes beyond the 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?

The description is two sentences, front-loaded with the primary purpose in the first sentence, and contains no filler. Every clause adds value—input format, output, and the nuance of the 'results' parameter are all covered without waste.

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's moderate complexity, the presence of a full output schema, and annotations that cover safety, the description is complete. It explains what the tool does, what input it expects, and what it returns. The agent can confidently invoke it without needing additional clarification.

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 description coverage is 100%, so all three parameters (n_boot, api_key, results) are already documented. The description reinforces the 'results' format ('list of item-ids or {item: score} dict') but does not add new semantic details beyond what the schema provides. 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?

The description opens with 'Audit a whole leaderboard from per-item results,' a specific verb ('audit') and resource ('leaderboard') that clearly differentiates this from sibling tools like verify_subset_win or verify_model_gap. It also states the concrete outputs—'rank confidence intervals + whether #1 is statistically real'—making the tool's purpose unmistakable.

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 clearly indicates the tool is for auditing a whole leaderboard, not for individual subset checks or gap verifications. It lacks an explicit when-not-to-use statement or named alternatives, but the context is clear enough that an agent can distinguish it from the sibling verification tools.

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