test_hypothesis

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

No annotations are provided, so the description carries full burden. It discloses that runs must have measurementRef, aggregation against baseline, and that no-improvement is NO_IMPROVEMENT (bumping failure counter). However, it does not disclose mutability, side effects, or auth requirements.

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, concise sentence that front-loads the purpose. It is not verbose, though breaking into smaller sentences could improve readability. Every part adds value.

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?

Given the complexity (nested objects, 3 required fields) and no output schema, the description is incomplete. It omits parameter details, return values, and usage context for the nested agentRuns array. Significant gaps remain.

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 0%, and the description adds minimal meaning beyond parameter names. It hints at measurementRef and aggregation but does not explain runId, hypothesisId, or fullTest structure. The description fails to compensate for the lack of parameter documentation.

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 records a full test of a hypothesis with 3-5 frontier agents, specifying the required measurementRef and aggregation behavior. It distinguishes from siblings like 'execute_full_test' by emphasizing the recording aspect, though not explicitly differentiating.

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 use after agents run the loop end-to-end and mentions aggregation rules, but does not explicitly state when not to use or compare with alternatives like 'execute_full_test'. Guidance is implied rather than explicit.

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