doctor

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

The description explicitly states 'Never mutates' and 'Dry-run only,' which are key behavioral traits indicating the tool is read-only and safe to invoke. This transparency helps an agent understand side effects without needing annotations.

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 brief and to the point, covering the essential aspects (dry-run, check items, non-mutating) in a compact form. It avoids redundancy, though the term 'shadowed' might be unclear to some users, slightly reducing clarity.

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?

While the description explains the tool's function and side-effect profile, it does not mention the output format or return value. For a diagnostic tool, this omission could leave an agent uncertain about what to expect, making the description somewhat incomplete.

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 has no parameters, so schema coverage is effectively 100%. The description does not need to explain any parameters, and adding more would be superfluous. The baseline of 3 applies here as there are no parameter details to clarify.

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's function as a dry-run check for skill roots existence, counts, shadowing, and binding path. It uses a specific verb ('check') and identifies the resource (skill roots/binding path), making its purpose understandable even without additional context.

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 mentions 'Dry-run only' and 'Never mutates,' which implies it is for non-destructive diagnosis, but it does not explicitly compare to sibling tools like get_binding or why. There is no guidance on when to prefer this tool over others, leaving the usage context implicit.

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