Evaluate Study Run

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

The description reveals many non-obvious behaviors: assessments are immutable, stale model evidence is rejected, external calculations are submitter-reported and not verified, omitted custom values remain unevaluated, and built-in errors are fitted-window rather than holdout. These go far beyond the annotations, which only provide generic hints, and meaningfully shape how an agent should invoke the tool.

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 dense but every sentence carries essential operational or behavioral information. It is front-loaded with the core purpose, 'Save an immutable assessment,' and then efficiently sequences the required workflow. There is no filler or redundant restatement of the schema.

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 tool's complexity, an output schema, and only generic annotations, the description covers the full lifecycle: initial hash generation, evidence submission, staleness, authentication constraints, completeness semantics, and unsupported edge cases. An agent has enough information to avoid common mistakes and to decide when this tool is appropriate.

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?

With schema description coverage at 0%, the description compensates by explaining the role of external_evidence and expected_basis_hash, including the ordering dependency and the requirement for finite numeric or strict boolean values. It also clarifies that submissions are submitter-reported. It does not explain run_id or policy_id beyond their names, but the workflow description provides enough context for correct invocation.

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 opens with a precise action, 'Save an immutable assessment,' which clearly identifies the tool as a write operation for creating a persistent evaluation of a study run. It distinguishes this from read-only sibling tools like list_study_evaluations or comparison tools by emphasizing immutability and submission of evidence. Despite not naming a sibling explicitly, the verb and resource are 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 provides an explicit two-step workflow: first evaluate without external_evidence to get report.basis_hash, then submit with expected_basis_hash. It also gives important usage conditions such as manual sign-off requiring a signed-in reviewer and being rejected for API keys, plus the no-automatic-champion-promotion caveat. It does not explicitly name alternative tools, but the usage context is clear.

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