wirk_review

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

With no annotations, the description carries the full behavioral burden and does most of it: it discloses that the call is refused, names the two distinct error codes and which case triggers each, and notes the proposal 'waits' (i.e., no side effect occurs). It doesn't describe the successful path in detail, but since the caller can never reach it that omission is minor.

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?

Compact and front-loaded: the decisive constraint ('as an agent this is refused') appears in the first clause. Every element — error codes, wait behavior, the terminal command — adds information. The CLI fragment is slightly cryptic but earns its place by showing the expected decision shape.

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?

Given no annotations, no output schema, and a tool the agent cannot successfully call, the description supplies what the agent actually needs: that it will fail, why, and who should do it instead. The remaining gap is the decisions payload format for a human-driven call, which the CLI example only partly conveys.

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 25%, and the nested decisions objects (id, revision, action, reason) are undocumented in the schema. The description partially compensates by mapping the CLI 'ID@N' to id+revision and '--reason WHY' to reason, and by exemplifying the 'accept' action. It never explains the decisions array, the accept/reject/defer enum, or the request_id/workspace_id params, so the compensation is only partial.

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 implies the tool submits decisions on proposals ('Only people decide proposals', the CLI form 'wirk review ID@N accept'), but never directly states the verb+resource the agent would be invoking. Instead it foregrounds the refusal, so an agent gets behavior more clearly than the core action. It does loosely separate itself from siblings like wirk_write and wirk_query, but not explicitly.

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?

It gives strong when-not guidance: as an agent this call is refused, both for your own proposal (not_authorized) and any other (person_required). It then routes to the right alternative — 'Your person decides at their terminal' — making the handoff unambiguous. It stops short of stating any condition under which the agent should call it, which is consistent but keeps it from a 5.

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