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

Goes well beyond the annotations: it states the direction of effect (can only reduce spend, never start or increase it), discloses a side effect the annotations don't capture (cancels a queued ad launch pending Meta review), and describes the idempotent no-op response. This is genuinely useful behavioral context for a destructive write.

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 core action and its spend-direction guarantee, followed by side effects and edge cases. Every sentence earns its place.

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 two-parameter mutation with no output schema and rich annotations, the description covers the safety profile, side effects, and the empty-result case. It stops short of explaining what a successful response contains, though the no-op behavior is addressed.

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 100%, so brandId and campaignId are already fully documented with their source tools. The description adds no parameter-level detail, which is the expected baseline when the schema does the work.

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 ('Stops real delivery on an active ad campaign') and reinforces it with a memorable metaphor ('the kill switch'). An agent can immediately distinguish this from siblings like archive_campaign or approve_post.

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?

Clear context for when it applies and what happens in the no-op case (no ad running or already paused). It does not name a resume/alternative tool, but the operation is unambiguous in scope.

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