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

Annotations already flag destructiveHint=true and non-idempotent; the description adds the crucial dry-run behavior ('Previews unless confirm is true'), the audit-gated acceptance rule, and reversibility for keyword pauses. This is materially more than the annotations convey and rules out the main risk of an accidental live 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?

Three dense sentences, front-loaded with the main action and effect, followed by the confirmation gate and the scope boundary. No filler and nothing repeated from the schema.

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?

No output schema exists, so the description carries the return-value burden; the dry-run preview is announced but not described (what a preview reports, how many items). Everything else an agent needs to call this safely is present.

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 75% and the one undescribed parameter is confirm, which the description fully explains ('Previews unless confirm is true'). It also reinforces the negative_terms constraint that terms the audit does not flag are refused, matching the schema's own note.

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?

Specific verb-plus-resource ('Apply the Google Ads fixes from audit_client') with the two concrete effects spelled out: pause flagged keywords and add chosen search terms as phrase-match negatives. It is clearly distinguishable from siblings ads_add_negative_keywords and ads_set_keyword_status because it is audit-driven and batched.

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?

Names the upstream tool (audit_client) as the source of inputs, states the acceptance condition ('Only items the audit flags right now are accepted'), and gives explicit exclusions ('Does not change budgets, extensions or Meta campaigns'). It also points to ads_set_keyword_status as the path to undo a keyword pause.

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