benchmark_propose

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

With no annotations, the description bears the full burden. It discloses a rejection behavior for proposals missing required dimensions or cases ('or it is rejected as a hand-waved benchmark'). However, it does not detail side effects, auth needs, or rate limits, offering limited behavioral context beyond validation rules.

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 highly concise with two sentences. The first sentence immediately states the action and source, and the second provides critical constraints. No superfluous information, each sentence serves a purpose.

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 description covers the core purpose and rejection criteria but omits details on the runId parameter, other fields in the benchmarks object, and the return value (no output schema). For a tool with complex nested input and no output schema, more context is needed for full understanding.

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 0%, so the description must compensate. It explains the meaning of taskValueDimensions, resourceDimensions, and cases by specifying they are required. However, other fields like oracle, qualityScale, comparisonRule are not covered, leaving some parameters semantically underdescribed.

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 clearly states the tool proposes benchmark scorecards built from real prior uses/failures, with specific verb 'propose' and resource 'benchmark scorecards'. It distinguishes from sibling tools like benchmark_run or benchmark_select by emphasizing the proposal of new benchmarks with required elements.

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 implies usage for creating benchmarks based on prior data and sets criteria for valid proposals, but does not explicitly state when to use versus alternatives or provide when-not scenarios. Usage guidance is implied through the required components, but no direct comparison to sibling tools.

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