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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation profile is covered. The description adds real context beyond annotations: it verifies operation kind, approval integrity, and state drift before sending, and warns against replaying uncertain outcomes. That is useful operational detail an agent could not infer from the schema.

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 action and scope, then the precondition, then the failure-handling rule. Every sentence carries information; wording is slightly compressed but not padded.

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 operation with no output schema, the description covers the precondition, pre-send verification, and post-failure reconciliation guidance. Only minor gap is the undocumented connection_context parameter, which is a system-supplied token.

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 33% (only customer_id is documented in-schema). The description references customer_id and draft_id as the inputs and ties draft_id to the prepare step, but adds no format or semantic detail for draft_id or connection_context. Baseline 3 is right for a partial-coverage schema where the description does little extra.

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 change a shared daily budget'), plus the exact set scoped ('complete explicitly listed set of affected campaigns'). It names the sibling it pairs with (google_ads_shared_budget_update_prepare), so an agent can distinguish it from the prepare step and from the non-shared google_ads_budget_update_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?

Explicitly states the prerequisite ('Accepts only a matching draft from ..._prepare') and adds a handling rule ('Uncertain outcomes must be reconciled without replay'). It doesn't spell out when-not-to-use or point to the reconcile tool by name, but the flow is clear.

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