chap.review.depth

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

With no annotations, the description carries the burden and does useful work: it discloses an output choice set (skip/spot_check/full), a side effect (recording a route_decision artefact), and that the answer is rule-derived. The schema property additionally covers the refusal condition and decimal-string convention, so behavior is not opaque.

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?

Two sentences, front-loaded with the action and decision outcomes, then the artefact side effect. No filler or repetition of schema details.

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?

The combination of description and schema covers purpose, decision inputs, optional hints object, error on empty hints, and the recording side effect. The main minor gap is the lack of an explicit return/response shape, though no output schema exists.

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 100%, so the schema already documents all four parameters and the artefact_routing_hints object in detail. The tool description does not add parameter-level information beyond mentioning routing hints, so baseline 3 applies.

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 ('Decide'), a concrete resource (review depth for a task), and the three possible outcomes (skip, spot_check, full), with the input signal (routing hints). This clearly separates it from siblings such as chap.review.request or chap.decide.approve/reject, which perform different review lifecycle actions.

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 'Decide how much review a task warrants' gives clear context for when to call it, and 'from its routing hints' tells the agent what data drives the decision. It does not explicitly name alternatives or state when not to use it, but the purpose is distinctive enough among the siblings.

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