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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the monetization model ($0.002 USDC per successful call, x402 on Base/Solana/Arc), the no-charge-on-failure policy, the dataset's archival date, and result ordering. These are material facts an agent cannot infer from structured fields.

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?

A single dense sentence that front-loads the identity and purpose before the field list and pricing. Efficient with no filler, though the enumeration of returned metrics is lengthy and partly duplicates the output schema.

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?

The complexity here is low (2 params, output schema present), and the description covers purpose, ordering, staleness, and payment requirements. Remaining details like exact response shape and pagination are handled by the output schema and the limit parameter.

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 'q' length bounds and 'limit' range/default are already fully documented. The description only adds that the query targets a model name and that results are ranked by average score, which is marginal beyond the schema.

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 and resource ('finds open-source language models by name'), names the exact dataset (Open LLM Leaderboard v2), scopes it to 4,576 rows, and enumerates the returned fields plus sort order. This clearly separates it from siblings like b2b_pgatour_leaderboard and b2b_hyperliquid_leaderboard despite the shared 'leaderboard' naming.

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 name-search use case and its constraint (model name part) make the intended invocation obvious, and the 'best average first' ordering tells an agent what it gets by default. No explicit when-not or alternative is named, but the domain is narrow enough that none is really needed.

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