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

Goes well past the annotations (readOnly/idempotent/openWorld), disclosing that filtering is applied to the complete ranked benchmark before pagination so positions stay global, that ties are preserved, and that rows are never deduplicated into method families. It also flags that responses include metric direction, completeness checks, invalid-percentage warnings and separate reporting/origin papers, which is exactly the behavioral context an agent needs before calling.

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?

Dense and front-loaded — the core selection semantics come first, followed by filtering/pagination behavior, then response contents. A couple of clauses ('Top N corresponds to limit N rows') duplicate the schema, but nothing is padding.

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 an output schema present and full annotation coverage, the description needn't explain return shapes, and it still covers pagination/continuation, global-position stability under filtering, tie handling and non-deduplication. An agent can call this correctly without further inference.

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 already 100%, and the description still adds cross-parameter meaning: limit is framed as 'Top N' rows and also as the page size for continuation, and the method substring's interaction with offset is restated so positions are understood as global. That is genuine added value, though it largely restates the schema's own wording rather than introducing new semantics.

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 concrete verb and resource: it returns individual reported result rows for one exact benchmark version/split and metric, with each row carrying resultId, configuration and global position. The clause 'not deduplicated or grouped into method families' implicitly contrasts it with an aggregation/ranking sibling, but no sibling is named explicitly, so differentiation is inferred rather than stated.

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?

Usage is implied rather than prescribed: the description explains that continuation should use results.nextCall and that a different metric starts at offset 0, and the schema points to discovery for the benchmark slug. It never says when to choose this over get_solution_rankings or get_company_leaderboard, nor when not to use it.

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