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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds useful workflow context (this consumes a prepared draft or an approval reference, and requires a plan digest plus the complete change set), hinting at verification before commit. It still omits what happens on digest mismatch, idempotency, and reversibility of the applied change.

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 leads with the verb and packs the two alternate invocation paths without filler. The phrasing gets tangled in the second clause, but nothing is wasted.

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, irreversible commit with 6 parameters, 17% schema coverage and no output schema, this is thin: the agent still lacks the meaning of "complete expected_changes," the connection_context requirement, and what the tool returns on success or digest failure.

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 description coverage is only 17% (just customer_id), so the description must carry the load — and it does: it documents 5 of 6 parameters and, crucially, the mutually exclusive relationship between (customer_id, draft_id) and (approval_ref, expected_plan_digest, expected_changes), plus the requirement that expected_changes be complete. Only connection_context is left unexplained.

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 verb is clear ("Confirm a prepared change") but the resource is left generic — the description never says it applies a budget change, relying on the tool name to disambiguate it from the ~40 other *_confirm siblings. Without the name, an agent could not tell this apart from google_ads_bidding_update_confirm or google_ads_campaign_create_confirm.

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 implies the intended position in the workflow (confirming something previously prepared) and gives conditional routing between two invocation paths (customer_id+draft_id vs approval_ref+expected_plan_digest). However, it never names the prepare counterpart explicitly, gives no when-not guidance, and does not warn that this step commits the change.

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