Model Route

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

Discloses behavior well beyond the annotations: the model is only called when TYPESAFE_API_KEY is set and offline is not true, otherwise a labelled offline estimate is returned, and model.source indicates which path ran. It also explains the deterministic+System One blend and the advisory-only contract. This is rich context an agent could not infer from readOnlyHint/openWorldHint alone.

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?

Front-loaded with the core purpose, then progressively adds the auth/offline condition, the advisory contract, and the host mapping. Dense but every sentence carries information; a touch long, but nothing is filler.

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 6-parameter advisory tool with no output schema but a markdown-report option, the description covers the return signal (model.source), the fallback path, and the host mapping. An agent has enough to call it and interpret the result, though it never mentions the 'top' impact-file parameter.

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 baseline is 3; the description still adds meaning by explaining what host does (maps the tier to that host's model id) and tying offline to the labelled-estimate fallback and model.source. It reinforces, though does not fully replace, the schema's parameter docs.

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+resource: 'Recommend a model tier (cheap, mid or premium) for a coding request before any work starts.' It also separates itself from siblings by noting it is advisory and 'never feeds review_gate or review_verdict', so an agent can tell it apart from the review tools without opening any 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 (use before any work starts, for routing a change request) and names the review_gate/review_verdict alternative it is not. It stops short of stating explicit when-not-to-use cases beyond the advisory disclaimer, but the routing intent is unambiguous.

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