check_conformance

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

With no annotations, the description fully discloses key behaviors: it's non-mutating (no token minted), applies deterministic rules first, surfaces advisories, and fails closed when unprovable. This is comprehensive for a dry-run tool and goes beyond generic wording to clarify the decision logic. The fail-closed detail is particularly valuable for an agent predicting outcomes.

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, with three sentences front-loading the key purpose and behavior. Every sentence adds value: the first explains what it does, the second details the rules, and the third gives usage guidance. No fluff or repetition.

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 (a dry-run with fail-closed logic) and the complete lack of output schema or annotations, the description covers all essentials: what it does, how it decides, and when to use it. The only minor gap might be the return format, but for a dry-run tool, the agent likely only needs to know the outcome, which is implied by 'see why something would be vetoed'.

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 compensate, and it partially does by explaining that the tool judges an 'artifact' against decrees, and that it's a gate for actions. However, it doesn't clarify the meaning of 'targets' or 'intent' beyond what the schema shows. The description does imply that 'action_type' and 'artifact' are core to the evaluation. Despite the coverage gap, the description adds enough semantic context to elevate above baseline 3, but not to 5 because 'targets' and 'intent' remain ambiguous.

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 it dry-runs the gate, judging an artifact against decrees without minting a token. It distinguishes itself from request_action by explicitly noting it's a dry-run, and from siblings like verify or validate_token by focusing on decree conformance rather than token validation.

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 provides explicit guidance on when to use the tool: 'Use before request_action to see why something would be vetoed.' This clearly signals the appropriate context, which is critical given the opaque sibling set. It also implies when not to use it (when you want to execute the action).

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