preview_fixes

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states the tool writes nothing, never writes, and works without a clone for GitHub repos. It also reveals that only auto-fixable findings for 10 of 21 rules are covered, setting accurate expectations.

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 short sentences with no filler: the primary behavior is front-loaded, input options are clearly stated, and the critical safety warning and alternative action are placed at the end. Every sentence earns its place.

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?

The tool has only two optional parameters and no complex schema, and the description covers behavior, safety, usage mode, and the alternative to actually apply fixes. No output schema is needed because the description explicitly says it returns the exact unified diff. The definition is complete for correct selection and invocation.

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%, with both dir and repo described. The description adds meaningful context beyond the schema: repo works without a clone, dir is for a local checkout, and the two are mutually exclusive. This helps an agent choose correctly without inspecting further.

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 ('Preview') and resource ('exact unified diff that gha-doctor --fix would apply'), and scopes it to auto-fixable findings across 10 of 21 rules. This clearly differentiates it from sibling tools like analyze_repo or lint_repo, which focus on analysis rather than presenting fixes.

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 explicitly explains when to use the tool (to preview auto-fixable diffs), how to invoke it (repo or dir), and when not to (to actually apply fixes, run gha-doctor --fix). The statement 'this MCP server never writes' reinforces that this tool is only for previewing, not applying changes.

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