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

Annotations declare destructiveHint=true and idempotentHint=false, and the description substantiates that with concrete failure modes: SEND_RAMP_LIMIT throttling with window/limit/remaining in the error, SENDING_PAUSED workspace review, and MESSAGE_NEEDS_REVIEW content hold. It also discloses the human-confirmation requirement and the escalation risk of repeated flags, none of which the annotations 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?

Front-loads the core action and required inputs in the first two sentences, then batches error handling. The error paragraphs are long and repeat 'do not retry' across cases, but each case carries distinct recovery instructions, so the length is mostly earned rather than padding.

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 13-parameter mutation tool with no output schema, the description covers inputs, human-confirmation prerequisites, throttling, pause states, and content-review holds thoroughly. It does not say what the call returns (e.g., a campaign id or status) or confirm the response shape after a successful send.

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?

At 69% schema coverage the description materially adds meaning by stating the mutual exclusivity of audienceId/segmentId/topicId and the html-vs-templateSlug choice, which the flat schema does not enforce. Minor inconsistency: it mentions a 'fully-qualified filter' but no filter property exists in the schema, which could mislead an agent.

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 clear scope: 'create a campaign and immediately schedule it to send, in a single call.' The phrase 'one-shot' and 'single call' distinguishes it from the create_campaign + schedule_campaign sibling pair an agent might otherwise compose.

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 real selection rules: pass exactly one of audienceId/segmentId/topicId/filter, and html OR templateSlug. It also specifies a pre-call workflow (confirm recipients, sender, subject, wait for a clear yes) and several explicit when-not-to-retry conditions. It stops short of naming sibling alternatives like schedule_campaign or send_email.

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