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

Annotations declare destructiveHint=true and openWorldHint=true but give no idea what is at stake. The description adds the critical consequence ('starts spending') and the two-phase preview-then-confirm behavior, which is exactly the kind of operational context annotations cannot convey.

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?

Two tightly written sentences, front-loaded with the effect ('starts spending') followed by the required call sequence. No filler.

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 mutation tool with no output schema, the description covers precondition, blast radius, and the confirmation protocol. It omits what the preview response contains and how the required 'reason' parameter should be populated.

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 50%; account and confirm are documented in the schema, and the description reinforces the confirm flow. However, 'reason' is a required parameter with no schema description and no explanation in the description, leaving a real gap for a required field.

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 with its precondition: turning a *paused* campaign on. The state transition implicitly distinguishes it from google_ads_pause_campaign, though the counterpart tool is never named explicitly.

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?

Gives a clear workflow: only applies to paused campaigns, first call returns a preview, ask the user to confirm, then re-call with confirm=true. It does not name alternatives (pause_campaign, update_campaign, set_status) or note when not to use it, but the two-phase confirmation guidance is concrete.

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