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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds only that output can optionally include raw prompt/model output, which largely restates the schema's include_output note rather than disclosing new behavior like pagination defaults or payload size 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?

A single front-loaded sentence with no wasted words or filler. It is efficient, though it is arguably too thin to carry the tool's full scope.

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 annotations covering the safety profile, return values and safety need not be explained. However, a six-parameter listing tool whose description omits any filtering or sibling-routing guidance is only minimally complete.

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% and every parameter (size, limit, model, offset, puzzle_id, include_output) is documented in the schema itself. The description adds no syntax, format, or interaction detail beyond what the schema provides, so it meets the baseline only.

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 names the specific resource ('individual benchmark runs') and defines it precisely as 'one model on one puzzle', which is genuinely clarifying. It does not, however, distinguish this list tool from siblings like get_model_results or get_puzzle_results that may return overlapping data.

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?

There is no when-to-use guidance, no condition selecting this over the sibling result tools, and no mention of how filtering should be applied. The agent must infer usage entirely.

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