test_hypothesis

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

With no annotations, the description carries full burden. It reveals some behavioral traits (e.g., outcome values like NO_IMPROVEMENT, never 'perfect'), but does not disclose side effects, idempotency, or behavior on repeated calls. Missing transparency on what happens after recording (e.g., aggregation, state updates).

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 concise and front-loaded, stating the main action in the first sentence. Additional clarifications about agent runs and outcome rules are useful. However, it could be better structured (e.g., separate sections for input-output behavior).

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 params, no output schema), the description is insufficient. It does not explain what the tool returns, how to construct the fullTest object, or what constitutes valid inputs beyond the mention of measurementRef. An agent would likely need additional information to use this tool correctly.

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%, requiring description to compensate. The description adds meaning to 'measurementRef' (must be tool-measured) and outcome classification, but does not explain 'runId', 'hypothesisId', or the full structure of 'fullTest' (e.g., valid values for 'model'). Incomplete parameter semantics.

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 defines the tool's purpose: recording a full test of a hypothesis involving 3–5 frontier agents, with specific requirements for measurement references and outcome classification. It is distinct from sibling tools like 'execute_full_test' or 'observation_record' due to the explicit mention of agent runs and baseline comparison.

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?

No explicit guidance on when to use this tool versus alternatives (e.g., 'execute_full_test' or 'observation_record'). The description only explains what it does, not the context of use, prerequisites, or when not to use it.

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