Environment Doctor

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds the inspection scope plus the existence of a 'notes' field for anomalies, which is useful behavioral context beyond the annotations, though it stops short of describing failure or partial-availability behavior.

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 labeled fragments (scope, when, exclusions, returns) with no filler and the trigger condition front-loaded after the scope. Every line carries selection-relevant information.

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 parameterless, read-only diagnostic with a rich annotation set and an output schema, the description supplies everything needed: what is checked, when to reach for it, which siblings to prefer instead, and a sketch of the response shape.

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 there is no argument semantics to explain – baseline 4 applies. The description correctly does not invent parameter guidance where none is needed.

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 ('Check the local toolchain') and enumerates exactly which tools are inspected (xcode, swift, node, ruby, git, uv, asc, fastlane, maestro, Java 17+, maestro-live). An agent can distinguish this from sibling diagnostics like config_doctor or pipeline_status without opening the schema.

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?

Uses explicit 'Use when' / 'Not for' framing, names the triggering condition ('something fails to run locally'), and routes the agent to the correct alternatives by name (config_doctor, setup_status) for the excluded credential/config case.

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