Dismiss a stopped draft

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

Adds real context beyond the annotations: required write scope (review_queue:write), OAuth scope luca:queue_ops, the mandatory Idempotency-Key and its fallback behavior, and that repeat dismissal succeeds. The destructive/idempotent hints are already in the annotations, so this is consistent reinforcement rather than the whole burden.

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 meaning and the idempotency reassurance before the API/auth metadata. The Luca operation, scope, and sensitivity lines are boilerplate but short and scannable; little waste overall.

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?

Covers auth scope, idempotency requirements, and workspace override for a destructive mutation, which is what an agent needs to call it safely; an output schema exists so return values need not be described. The only missing piece is explicit sibling routing.

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?

With 75% schema coverage the schema already documents workspaceId, workspaceSlug, and idempotencyKey, and the description largely restates those. The turnId parameter (the only required one, a UUID referencing a drafting turn) gets no explanation beyond the endpoint path template, which is the main residual gap.

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 (remove/dismiss) and resource (a drafting turn), plus the qualifying states (cancelled, paused, failed). 'Without drafting again' distinguishes it from the retry/regenerate siblings without needing their schemas.

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 precondition (only cancelled, paused, or failed turns) tells the agent when this applies, and 'without drafting again' implicitly steers away from retry/regenerate. It does not name the alternative sibling tools (drafting_cancel, drafting_retry) explicitly, so routing still requires a small inference.

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