benchmark_tuning_candidate

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

Annotations already indicate read-only and non-destructive, so the bar is lower. The description adds behavioral context by disclosing interleaved exactly-once sampling and snapshot-consistent duplicate-aware result comparison, which explains how execution occurs without contradicting the 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?

The description is a single dense sentence that front-loads the core action and then specifies the key methodological details. No filler words.

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 12 parameters and an output schema, the description provides a high-level summary of purpose and method. It doesn't mention required session/candidate identifiers, but those are evident from the schema. The presence of an output schema reduces the need to describe return values. Some context on the benchmarking process is omitted, but the description is adequate.

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 67%, with most parameters individually described in the schema. The tool description itself does not explain any parameters, but the schema's descriptions for parameters like runs, phase, and prove_equivalence carry that burden. Thus, the description adds no extra parameter semantics but doesn't need to.

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 'Benchmark' and identifies the resource as 'one rewrite candidate', distinguishing it from sibling tools like benchmark_index_candidate. It also specifies the methodology (interleaved, exactly-once samples, snapshot-consistent comparison), making the purpose unambiguous.

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 clearly indicates this tool is for benchmarking a single rewrite candidate, which provides context vs. siblings like benchmark_query_rewrite. However, it does not explicitly state when to use this vs alternatives or mention exclusions, so it stops short of full usage guidelines.

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