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

Annotations already declare destructiveHint=true, but the description adds the crucial context the annotation cannot: the action is irreversible, and it 'changes nothing in the Google Ads account' (i.e. no account mutation, only proposal state). That materially sharpens how the agent interprets the destructive hint.

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?

One tight sentence with the destructive/irreversible fact front-loaded, followed by the remedy and the account-impact clarification. 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?

For a single-param, no-output-schema tool, the definition covers irreversibility, account impact, and the re-propose path. The remaining gap is that it never contrasts with undo_changes, which is the sibling an agent is most likely to weigh against it.

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?

Only one parameter with 100% schema coverage, and the schema already explains it is 'the proposal_id a propose tool returned'. The description adds no formatting, sourcing, or validation detail beyond that, so baseline 3 applies.

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 (marks as discarded) on a specific resource (an open proposal) and defines the terminal consequence ('can never be applied'). The agent can distinguish this from apply_changes, propose_changes and undo_changes without opening any 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?

Gives the precondition ('an open proposal') and an explicit recovery path ('propose again instead'), which tells the agent what to do after discarding. It does not, however, say when to prefer this over undo_changes, the closest sibling in the list.

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