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 value beyond them: the blast radius ('stops every ad and keyword inside it') and the confirm=false dry-run affordance, neither of which is in the annotations or schema. It stops short of covering idempotency or permission/auth requirements.

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?

Front-loaded with the core verb/resource, then sibling disambiguation, then behavioral caveat and dry-run. Every sentence carries information, though the synonym lists ('enable / resume / unpause / reactivate') are slightly 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?

An output schema exists, so return values need no explanation. Given a mutation tool with 0% schema coverage, the description supplies the pieces an agent needs: what changes, blast radius, sibling routing, and the dry-run escape hatch.

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 0% and there is no enum on status, so the description must compensate — and it does for the two non-obvious params, defining status values ('ENABLED' / 'PAUSED' with synonym sets) and confirm's dry-run semantics. customer_id and ad_group_id are left to naming inference, and status synonyms are prose rather than machine-readable, so it is strong but not complete.

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+resource ('Turns a Google Ads AD GROUP on or off') with the exact status values enumerated, and it explicitly places itself among siblings (update_campaign_status / update_ad_status) as 'the missing middle level'. An agent can distinguish it from every neighboring status tool without opening a 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?

It names the alternatives and the selecting condition, and warns that pausing keywords one by one does NOT stop the group's ads, explicitly steering the agent to this tool for switching off a wasteful theme. When-to-use and when-the-alternative-is-wrong are both stated.

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