delimit_lint

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

Given no annotations, the description reveals auto-chaining behavior, dry_run side effects, and pass/fail outcome. However, it lacks details on normal mode side effects (e.g., what gets recorded or notified) and does not fully explain the auto-chain sequence.

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 mostly concise and front-loaded with purpose. It could be slightly more structured (e.g., bullet points) and shorter by omitting 'Primary CI integration point' which is implied.

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, return values are covered. The description covers purpose, dry_run behavior, and integration context. It lacks details on error handling or prerequisites (e.g., valid specs), but overall is fairly complete.

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 baseline is 3. The description adds value for the dry_run parameter by explaining its behavioral implications. Other parameters (old_spec, new_spec, policy_file) are not elaborated beyond schema, but the dry_run detail justifies a 4.

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 the tool lints two OpenAPI specs for breaking changes and policy violations, and positions it as the primary CI integration point combining diff and policy. This distinguishes it from related siblings like delimit_diff and delimit_gov_evaluate.

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 explains when to use dry_run (for CI preview without side effects) and implies normal mode for full enforcement. However, it does not explicitly contrast with sibling tools or state when to use alternatives.

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