Diagnose what to fix

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

Annotations already declare this a read-only, idempotent, non-destructive, closed-world operation, so the safety profile is covered. The description adds real value by disclosing the result content — filtered failing/warning validators, their messages, structured findings, and suggested next actions — which is important since no output schema exists. It stops short of describing the finding shape or whether any auth/setup is required.

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?

One dense sentence that front-loads the action ('Run guard') and then enumerates the output, with no filler or redundancy. Every clause contributes to telling the agent what it gets back.

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 one-optional-parameter, no-output-schema tool, the description does the needed work by summarizing the returned content and its agent-facing framing. It could be slightly more complete by stating whether findings are paginated or how next actions are represented, but nothing essential to calling it correctly 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?

There is a single optional parameter (projectDir) with 100% schema description coverage, so the schema fully documents path resolution and the default. The description adds nothing about the parameter, which is an acceptable baseline when the schema already carries the semantics.

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 names a specific action (run the guard) and a precisely scoped output (only failing/warning validators with messages, structured findings, and suggested next actions), which clearly signals a filtered diagnostic rather than a full report. It distinguishes itself implicitly from docguard_guard (which presumably returns everything) but never names any sibling outright, so differentiation is inferable rather than stated.

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?

Usage is implied by 'shaped for an agent to act on' and by the 'only what needs fixing' framing, which suggests this is the triage-then-fix entry point. However, with ten sibling tools (including docguard_guard, docguard_report, docguard_score, docguard_explain), no explicit when-to-use or when-not-to-use guidance is given, leaving the agent to infer the boundary.

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