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

Annotations already declare destructiveHint=true and openWorldHint=true; the description goes beyond them by spelling out the real-world cost consequence (daily budget starts spending) and an approval requirement ('Requires human approval; never auto-approved') that appears nowhere in the structured fields. It doesn't cover failure behavior if the campaign isn't published, or what the response contains.

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?

A single front-loaded sentence with a bracketed tag prefix; the cost consequence and approval caveat land last where they read as the most important warnings. 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 money-spending mutation with no output schema, the description covers the key agent-facing facts: identifier options, the spending effect, the external-provider target, and the approval gate. Missing only the not-published failure case and any return-value expectation.

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 0%, so the description must carry the identifier semantics – it names both `ads_campaign_id` and `ads_campaign_uuid` and signals they are interchangeable ('or'). That is real added meaning, but it doesn't state that at least one is required (both default to null, 0 required params) nor any format detail for the UUID.

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 ('Switch a published ad campaign ON at the provider') plus the concrete consequence 'it starts spending its daily budget'. This clearly distinguishes it from pause_ads_campaign and publish_ads_campaign, which occupy adjacent lifecycle stages.

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?

The precondition 'published ad campaign' tells the agent the campaign must already be published (i.e. use publish_ads_campaign first), and the human-approval note sets the operational context. It stops short of explicitly naming pause_ads_campaign or publish_ads_campaign as alternatives, so it earns a 4 rather than a 5.

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