task_doctor

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

readOnlyHint=true already tells the agent this is a safe, non-mutating operation, so the description's main added value is the list of areas inspected. It does not say whether the tool reports problems, throws on failure, or how severe findings are surfaced, which matters for a diagnostic tool.

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 verb first and the scope enumerated after the colon; no filler. The list items ("view drift", "log") are terse to the point of being cryptic, which slightly undercuts the efficiency.

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?

With no parameters, no output schema, and a read-only annotation, the definition is close to sufficient, but it leaves unclear what a diagnosis returns and whether a failure result is an error or a report. For a tool whose whole job is reporting findings, that gap is noticeable.

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 nothing for the description to disambiguate; baseline 4 applies. The colon-separated list of checks gives the agent a mental model of scope without implying any input it must supply.

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 ("Diagnose") and resource ("the project") and enumerates the checks performed: root, configuration, registry validity, view drift, log. An agent knows exactly what the tool inspects, though it never distinguishes itself from plausibly overlapping siblings such as task_validate or quality_check.

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 versus task_validate or quality_check, no prerequisites, and no exclusions. The word "Diagnose" hints at troubleshooting, but with two sibling tools that could equally sound diagnostic, the agent is left to infer the routing decision.

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