doctor

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

No annotations are provided, so the description carries the full burden. It never states that this is a read-only diagnostic, whether the cached 'models' data can be refreshed, what permissions or auth the 'health' check requires (install, sign-in, quota are only in the schema), or how expensive/slow a health probe is.

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?

It is a single compact sentence with no filler and the mode distinction is front-loaded, but the telegraphic clause-splicing ('efforts, output prices, approval need; or backend health') is cryptic enough that terseness costs comprehension rather than buying it.

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 three-optional-parameter tool with no annotations and no output schema, the description should clarify both modes and the effect of detail/backend. It only sketches the models mode's outputs and leaves health-mode behavior and parameter effects to be inferred, which is insufficient given the missing structured support.

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 description coverage is only 33% — 'scope' is documented in the schema, but 'detail' and 'backend' are bare enums with no explanation in either place. The description hints at 'per backend' and full output contents but does not explain what 'detail: full' adds or what the 'agy'/'codex'/'claude' backends differ in, so the low-coverage gap is not compensated.

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 names the resource ('models per backend') and enumerates specific outputs (efforts, output prices, approval need), plus an alternative mode (backend health). However, it omits an explicit verb and is written as a telegraphic noun phrase, so the agent must infer that this is a diagnostic/reporting tool rather than, say, a configuration setter.

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 phrase 'or backend health' implies the two modes and roughly matches the scope enum, giving implied usage. But there is no explicit guidance on when to prefer health vs models, and no differentiation from siblings like consult, review, or issue, which an agent would need to route correctly.

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