env_doctor

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

No annotations are present, so the description must carry the behavioral load. It usefully enumerates the exact surface being probed (xcode, swift, node, asc, fastlane, uv, git, maestro, Java 17+, maestro-live), which tells the agent the coverage scope, but it never says whether the tool only reads or also installs/repairs, nor what a passing vs failing result looks like. The presence of a check-style name plus a defined output schema partially compensates.

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?

A single front-loaded sentence with the action and the full checklist; every clause carries information. It is dense but not padded, though the trailing parentheticals slightly interrupt the scan.

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-argument diagnostic with an output schema that already documents return values, the description's enumeration of checked toolchain components is close to sufficient. The main gap is the absence of any routing guidance relative to the other diagnostic tools.

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, which is the baseline-4 case. The description adds no parameter meaning because there are none to describe.

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 gives a specific verb+resource ('Check the local toolchain') and enumerates exactly which components are inspected, so an agent knows precisely what this tool reports on. It does not, however, differentiate itself from adjacent diagnostic siblings such as config_doctor or setup_status.

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?

There is no statement of when to run this tool versus config_doctor, setup_status, or orchestrator_preflight, all of which are diagnostic siblings in the same namespace. The parenthetical notes ('app creation only', 'end-to-end flows, Viewer') describe scope of checks, not usage conditions.

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