prgenius_doctor

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

With annotations already covering the safety profile (readOnly, idempotent, non-destructive), the description goes further and enumerates the concrete checks performed (versions, KB readability/coverage, gh CLI, MCP registration, sample analyze, warnings). Since there is no output schema, spelling out the return dict keys is genuinely additive behavioral context.

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?

Purpose and precondition are front-loaded in two tight sentences. The 'Returns' block is somewhat long, but each key listed is load-bearing given no output schema exists, so the length is largely earned.

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?

For a zero-param diagnostic with no output schema, the description supplies both the invocation precondition and the shape of the result (ok, versions, kb, gh, mcp, sample, warnings). Nothing an agent needs in order to call or interpret it is missing.

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?

The tool takes zero parameters, so per the rubric the baseline is 4. The description correctly implies a no-argument invocation and has no parameter semantics to get wrong.

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?

States a specific verb and resource ('Self-test the pr-genius install') and instantly separates itself from the analysis siblings by framing itself as a pre-flight health check. Nothing about what it does is left ambiguous.

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?

Explicitly prescribes the usage condition: 'Run this before trusting analyze_pr output.' That names the sibling whose reliability it gates, which is exactly the routing signal an agent needs to pick this tool over analyze_pr or status_prs.

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