Benchmark leaderboard

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

No annotations provided, so the description carries the full burden. It discloses the auto-source-selection behavior, that headers warn about incomplete data, that estimates are marked with * and footnoted, and that refresh bypasses cache. Strong behavioral disclosure, though it doesn't state auth needs or rate limits.

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-loaded with purpose and auto-selection logic, then args in a clear list. Every sentence earns its place, though the eval slug examples in the arg list are slightly verbose.

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?

Despite 8 params, no annotations, and no output schema, the description covers purpose, source-selection behavior, estimate marking, cache behavior, and all parameters. Missing only auth/rate-limit context or return-format hints, but otherwise complete for an agent to invoke 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?

Schema coverage is 0%, so the description must compensate entirely, and it does: it documents all 8 params with meaning beyond types (benchmark accepts key/label/slug, top default 15, fields as comma list overriding defaults, creator substring match, open_weights filter, min_intelligence threshold, include_estimates default True with marking behavior, refresh bypasses cache).

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 a specific verb (rank) and resource (models on one benchmark) and explicitly names the honesty constraint about source/coverage. Distinct from siblings like aa_leaderboard (general) and aa_model (single model detail).

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?

Explicitly explains the auto-selection hierarchy (700-row leaderboard > curated eval chart > homepage panel) and warns when it falls back to a non-full leaderboard. This tells the agent exactly when this tool is appropriate versus alternatives.

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