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

Goes well beyond the annotations by disclosing that the operation only stages a change, that applying is permanent, and that the account is not modified. Annotations only give readOnlyHint=false and destructiveHint=false, so the staging-vs-applying distinction and the permanence warning are meaningful additions the agent would otherwise have to guess.

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?

Four short sentences with zero filler, front-loaded with the action and the non-mutation guarantee, followed by the confirmation workflow. Every sentence earns its place.

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?

Complete for a staging tool: it covers what it does, what it does not do, what it returns (proposal_id and preview), and the required follow-up call. With an output schema present and full param coverage, no further detail is needed.

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 coverage is 100%, so platform, entity_id, account_id and campaign_id are all documented in the schema, including the Taboola and DV360 platform-specific caveats. The description adds no parameter semantics of its own beyond the returned proposal_id, so the 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 and resource ('Stage deleting an ad set') and immediately scopes what it does not do ('Does NOT change the account'). This cleanly separates it from siblings apply_change, undo_change and the other propose_* tools.

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?

Explicitly sequences the workflow: show the preview, then call apply_change(proposal_id) only after the user confirms. It names the alternative tool and the condition that gates the transition, leaving nothing to inference.

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