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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description is consistent with that. It adds real behavioral context beyond the annotations: it verifies operation kind, approval integrity, and state drift before sending, and warns that uncertain outcomes must be reconciled rather than replayed.

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?

Three dense sentences, front-loaded with the verb and resource, then prerequisites, then the failure-mode warning. Every sentence carries information; 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 destructive confirm tool with no output schema and three parameters, the description covers the prerequisite draft, the pre-send verification, and the no-replay rule. The only real gap is the undocumented connection_context parameter.

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 only 33% (only customer_id is documented as a 10-digit id). The description clarifies that draft_id must be a matching draft from the prepare step, adding meaning beyond the schema, but connection_context is never explained in either place.

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: confirm the replace of a Performance Max asset group's status or final URLs. It is clearly differentiated from the prepare sibling by naming the matching draft it consumes.

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 requires a draft produced by google_ads_asset_group_update_prepare, which tells the agent this is the second half of a two-step flow. The line about reconciling uncertain outcomes points toward the reconcile path, though the specific tool is not named as an alternative.

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