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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the agent knows this commits a mutation. The description adds that confirmation applies to a single typed draft reviewed via a diff, which is useful context, but says nothing about reversibility, idempotency, draft expiry, or what happens if the draft is stale.

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?

A single sentence with no filler, front-loading the action and the object, and packing the review precondition into the same clause.

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 step with no output schema, the description should at least note that it executes the pending mutation and what the caller gets back (e.g., a mutation receipt). The prepare/confirm pattern is inferable from siblings, so the gap is moderate rather than severe.

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. The description's 'draft' wording implicitly explains draft_id, but connection_context (a patterned context token) and the required-ness semantics of draft_id get no explanation in either schema or description.

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 (confirm) and resource (one typed entity-update draft), and the phrase 'after reviewing its before/after diff' ties it to the prepare/confirm workflow. It doesn't name the sibling google_ads_entity_update_prepare explicitly, but the draft concept makes the pairing inferable.

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?

'Confirm one typed entity-update draft after reviewing its before/after diff' implies the precondition (a draft exists and its diff was reviewed) but never states when NOT to use it, that it must follow google_ads_entity_update_prepare, or how it differs from other *_confirm siblings such as google_ads_management_confirm.

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