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 covered. The description adds genuinely non-derivable behavior: it verifies operation kind, approval integrity, and state drift before sending, and warns that uncertain outcomes must not be replayed. That is meaningful context for a mutation tool.

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 tight sentences, front-loaded with the action and its inputs, followed by the precondition and the failure-mode rule. No filler, though the phrasing is dense enough that the reconciliation sentence could be clearer about which tool to use.

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 two-step confirm with no output schema, the description covers the source of the draft, the pre-send validations, and the non-replay rule for uncertain state. It is nearly complete; only the explicit pointer to the reconciliation tool is missing.

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 33% (only customer_id is documented), so the description must carry weight. It ties draft_id to its origin in the prepare tool, which clarifies the parameter's provenance, but adds nothing about connection_context or the format/constraints of draft_id beyond what the schema shows. Marginal add over structured data.

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+resource ("Confirm add a negative keyword to a Search campaign") and names the exact sibling that produces its input, google_ads_negative_keyword_add_prepare. An agent can distinguish this confirm step from the prepare step and from the many other *_confirm siblings without opening any schema.

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 precondition: it "Accepts only a matching draft from google_ads_negative_keyword_add_prepare." It also gives a routing instruction for the failure case ("reconciled without replay"), which points toward reconciliation tooling. It stops short of naming google_ads_mutation_reconcile as the alternative, so the routing is implied rather than explicit.

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