doctor

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

With no annotations present, the description carries the full burden and does well: it enumerates what repairs mutate (remove orphan keys, prune default-matching entries, drop unknown top-level keys), states read-only-by-default, and discloses the important restart caveat for gating changes to take effect. It omits permission requirements and reversibility/backup of the destructive prune step, so not a 5.

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 core action and default are front-loaded, and the parenthetical list of what gets reported is dense but informative. It is a long single paragraph, but each clause adds distinct diagnostic detail rather than padding.

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 single-param maintenance tool with no annotations and no output schema, the description covers what is reported, the safe default, the mutation scope, and the restart side effect. It is nearly complete, only missing return-format/pagination-style detail (not strictly needed) and permission context.

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?

Schema coverage is 100%, so the schema fully documents fix, and the description's statement of what fix=true does largely mirrors the schema text. Baseline 3 is appropriate since the structured field does the heavy lifting.

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/repair) applied to a specific resource (the AQUA config file at a concrete path). No sibling tool does anything comparable, so the agent can identify it immediately 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?

Gives clear context for use — it names the exact symptom it addresses ('Unknown tool in enabled_tools' startup warnings) and separates diagnose-only from repair via fix=true. It lacks explicit when-not-to-use guidance or named alternatives, so it falls just short of a 5.

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