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

Annotations already mark the tool destructive, non-read-only, and closed-world; the description adds the important clarification that no Meta write occurs despite the local discard. It does not detail reversibility or auth, but the annotation coverage plus the no-Meta-write note is strong.

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 tight sentences, front-loaded with the action and followed by the important no-write and lost-token guidance. No filler.

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 tool has one required param and an output schema, and the description covers the draft types, the token requirement, the no-Meta-write behavior, and the lost-token alternative. That is sufficient for correct invocation.

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?

The sole parameter is confirm_token and schema coverage is 0%, but the description compensates by requiring the exact token for the prepared draft and by routing lost-token cases to the approval flow. It does not specify token format, but it gives the semantic source and fallback.

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 gives a specific action (discard) and enumerates the draft types (QuickCreate, recreate, ad-copy, structural-clone), and it ties the action to the prepared draft's confirm_token. It also distinguishes this from the approval-deny path for a lost token, so an agent can tell it apart from operations_deny_approval.

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 states the key usage context: pass the exact confirm_token for an existing prepared draft, and if the token is lost use operations_get_approval followed by operations_deny_approval. It does not explicitly discuss launch_confirm or other deny siblings, so it is clear but not exhaustive.

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