aiworkhub_agent_accept_preview

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

Annotations only declare readOnlyHint=true, and the description adds real depth: it writes nothing, names the cheap blocker set, gives the empirical failure rate, and carefully defines the semantics of `blocked` False as only 'nothing cheap is refusing yet.' It stops short of describing output shape or what happens on malformed inputs, but materially exceeds the annotation.

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-loads the read-only scoping and the core distinction in the first line, then adds the caveat about what a clear preview means. The measured 49/159 statistic is persuasive but somewhat heavy for a tool description; otherwise tight and well-structured.

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?

An output schema exists so return values needn't be described, and the description fully covers scope, safety, and the limits of the signal. The remaining gap is the undocumented confirmation and reviewer-request parameters, which an agent would have to guess at.

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 0% across 6 parameters, so the description must compensate and it only does so for one: `requested_risk_tier` is explained well (unset reads the finalizer's measured tier; explicit can only raise it). `confirm_high_risk`, `confirm_destructive_change`, and `reviewer_request_ids` are left entirely undocumented in both schema and description, so the compensation is 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?

States a specific verb+resource ('preview what would block accept_review') and explicitly scopes it as the cheap, no-write half of the acceptance flow. The contrast with accept_review is unambiguous, so an agent can choose between them without opening either 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?

Explicitly says to run this before accept_review, enumerates the blocker classes it checks (lens running, target not review_ready, approval missing), and warns that a clear preview is not an acceptance. It also states what it does NOT cover — tree materialization, validations, gate, receipt verification — which is exactly the exclusion guidance an agent needs.

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