recommend_benchmark

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds that this tool evaluates two specific tools against a ground-truth corpus, but it does not disclose whether models are fit, results are cached, or other side effects occur. No contradiction with 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?

A single sentence with zero filler. The action ('Score'), target ('sp.recommend / sp.audit'), and context ('ground-truth corpus') are all front-loaded, and nothing extraneous is included.

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?

For a tool with a rich output schema and detailed parameter descriptions, the core purpose is stated clearly. However, the description omits decision context such as when to prefer this over verify_benchmark or verify_recommendation, and what 'ground-truth corpus' concretely means. This is a moderate gap given the enormous sibling list.

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 the parameter descriptions are already detailed (e.g., fit, detail, as_handle, data_path). The tool description adds no parameter-level meaning beyond the schema, so the baseline of 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 uses a specific verb ('Score') with a clear resource ('sp.recommend' / 'sp.audit') and context ('against the ground-truth corpus'), making it distinguishable from the many estimation tools like recommend and audit. However, it does not differentiate from similarly named verification siblings like verify_benchmark or verify_recommendation.

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 gives no guidance on when to use this tool versus alternatives, nor does it mention exclusions or prerequisites. The phrase 'against the ground-truth corpus' loosely implies a benchmarking context, but there is no explicit routing information, which is especially important given the large sibling list.

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