run_eval

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

Annotations already establish the read-only, idempotent, non-destructive profile, so the bar is lower; the description adds real behavioral rules beyond that: every rule and the total must reach min_agreement, and a rule without human labels cannot pass. It does not explain scoring cost, latency, or what a failing result looks like, so a 4 rather than 5.

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?

Three dense clauses with no filler, front-loaded on what is measured before moving to the draft override and the pass constraint. It is slightly packed, but every sentence adds a distinct constraint.

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?

With an output schema present, the description needn't describe return values, and the annotations cover safety. It covers the core evaluation semantics and the draft path; the only real gap is the meaning of scorer and rules_version for a 4-parameter tool.

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%, so the description must carry the load, but it only covers two of four parameters: rules_yaml (draft, unsaved evaluation) and min_agreement (the pass threshold). The scorer enum values and rules_version are given no meaning at all, leaving half the surface unexplained.

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 gives a specific verb and resource ('measure a rule set against the hand-graded calls') and enumerates the outputs (per-rule agreement, quote validity, pass/fail), which clearly separates it from read-only siblings like get_rules. It does not explicitly name an alternative tool, so it falls just short of the 5 bar.

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?

It states the timing context ('before it ships') and a distinct mode of use ('Pass rules_yaml to test a draft rule set without saving it'), which is genuine when-to-use guidance. It stops short of naming alternatives or stating when NOT to call it.

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