fix_preview

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

With no annotations, the description carries the full burden and does so well: it discloses the read-only guarantee explicitly, describes the internal verification loop ('re-linted to prove the findings disappear and none are introduced'), and notes that unfixable items are reported separately. These are non-obvious behavioral traits an agent could not infer from the name.

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?

Front-loaded with the core action and a concrete enumeration of fix kinds, then closed with the two most decision-relevant facts (no writes, manual items listed). The middle sentence is dense but every clause maps to a distinct behavior; no filler sentences.

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?

An output schema exists, so return shape need not be explained. Given the tool's simplicity (one path parameter, no nested objects), the description covers scope, fix categories, safety posture, verification, and follow-up action — sufficient for an agent to call it 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 description coverage is 0% and the single `path` parameter has no schema documentation, so the description must compensate. It does: 'a workflow file (or every workflow under a directory)' clarifies that the argument accepts either a file or a directory and implies recursive scope, which is meaningful semantics beyond the bare string type.

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?

Opens with a specific verb and artifact: 'Show a unified diff of the safe automatic fixes for a workflow file'. It then enumerates exactly which fix categories are covered (permissions scoping, expression injection into env, set-output replacement), which distinguishes it from lint_workflows (finding problems) and pin_actions_plan (pinning actions) without ambiguity.

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?

'Never writes the file: apply the diff yourself' gives a clear operational contract, and 'Lists what needs a manual change' tells the agent this is a proposal, not an application. It stops short of naming an explicit alternative or prerequisite (e.g. run lint_workflows first), so the routing signal is strong but not fully spelled out.

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