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

Beyond annotations (readOnly=false, destructive=true), the description discloses that no Meta write is performed and that the effect is discarding a prepared draft. It doesn't mention irreversibility or auth, but this is adequate for a simple discard token operation.

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 concise sentences; first sentence states verb, object, and required parameter immediately; second sentence adds an important side-effect disclaimer and fallback. No fluff.

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 one-parameter action with output schema present and clear sibling fallback, the description covers token precision, no external write, and the lost-token path. It doesn't explicitly state whether the operation is idempotent or reversible, but these are minor for this use case.

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 provides only a string confirm_token with no description. The description adds 'exact' token requirement and says the token identifies the prepared draft secret token. It also routes lost-token users to operations_get_approval/operations_deny_approval. A little more detail on token provenance would be helpful, but this compensates well.

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 opens with a specific verb ('Discard') and names the exact resource types it affects (prepared QuickCreate, recreate, ad-copy, or structural-clone drafts). It also distinguishes this tool from approval-related operations by stating it works only with an exact confirm_token and performs no Meta write.

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 explicitly routes lost-token users to operations_get_approval then operations_deny_approval, which clarifies when NOT to use launch_deny inductive. It also notes 'No Meta write', helping the agent understand this is a local cancellation, not an external Meta-side denial.

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