Reject a queued draft

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

Despite annotations already covering destructiveness, the description adds substantial context beyond them: it names two side effects ('stops any related booking-recovery cadence', 'emits review.rejected'), lists required scopes and data sensitivity, and explains the Idempotency-Key requirement. Crucially it resolves the tension with idempotentHint=false by telling the agent retries are only safe when a stable key is supplied.

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?

The behavioral payoff is front-loaded in sentence one, followed by a compact metadata block. Every sentence is informative, though the endpoint/scope/transport details read as boilerplate appended rather than integrated into the narrative.

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 destructive, scoped mutation with an output schema (so return values need not be described), the definition covers side effects, auth requirements, idempotency, workspace scoping, and the endpoint. Nothing needed to invoke it correctly is missing.

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 schema coverage at 75%, the schema already documents workspaceId, workspaceSlug, and idempotencyKey. The description still adds value by stating why idempotencyKey matters (safe retries, server-generated fallback) and clarifying the workspace-override semantics, going slightly beyond the schema text.

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 first sentence gives a specific verb+resource plus the consequence ('Reject a pending review-queue draft so it never sends'), which distinguishes it from siblings like luca_review_queue_approve and luca_review_queue_restore without needing their schemas. It also names the concrete effect on the review-queue lifecycle.

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 description establishes the precondition (a pending draft) and the outcome, so usage is implied, but it never explicitly routes the agent away from approve/restore/explain siblings or states a when-not condition. Guidance is adequate but not directive.

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