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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description still earns credit by spelling out the practical consequence ('Nothing is signed and no money moves') and by disclosing what comes back: met or not met per milestone with the reason. It does not cover error behavior for malformed proofs, which keeps it from a 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?

Two sentences, front-loaded with the core action and immediately followed by the no-side-effect guarantee. Every clause carries information; nothing is padding or restatement of the title.

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 no output schema, the description usefully states the return shape (per-milestone met/not-met plus reason), and the nested brief structure is covered by the schema. What is missing is guidance on how a malformed or mismatched proof is handled and what the three kinds imply for input formatting, but the definition is otherwise sufficient to invoke the 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 100%, so the baseline would be 3, but the description adds genuine meaning by unpacking the enum values: checkrun is a CI check run, observation a FHIR Observation, oru an HL7 ORU message, which the schema only labels 'what the proof is'. It also frames the brief as the milestone set being judged, clarifying how brief and proof relate.

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 states a specific verb and resource: it applies IRIS's referee rules to a single proof (CI check run, FHIR Observation, or HL7 ORU message) evaluated against a brief's milestones, returning met/not-met plus reason. That is far more specific than the title alone. It does not explicitly name a sibling to contrast with, so it stops short of a 5.

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?

Usage is implied rather than stated: 'applies the rules referee IRIS runs' positions this as the evaluation step in a milestone flow, and 'Nothing is signed and no money moves' hints that this is a dry check rather than a commitment. However, it never says when to call this instead of a submission or milestone tool from the sibling list, nor any prerequisites.

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