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

Annotations already declare destructiveHint=true, openWorldHint=true, and idempotentHint=false. The description adds genuinely new behavior: a documented 403 SENDING_PAUSED refusal mode, the guarantee that nothing was sent in that case, and the instruction to route the user to support. That is meaningful failure-mode disclosure beyond the structured hints.

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 short sentences, no filler; the purpose leads, the user-confirmation rule follows, and the error path closes. Every sentence carries distinct actionable information.

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 non-idempotent, destructive, open-world send with no output schema, the description covers purpose, a precondition, and a key failure mode. It stops short of stating that a real email is dispatched from the workspace to a real address, which the destructive/openWorld hints imply but the text never makes explicit.

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 all three parameters (apiKey, testEmail, campaignId) are already documented in the schema, and the 100%-coverage baseline is 3. The description only adds the 'test address' confirmation nudge, which maps loosely to testEmail, and says nothing about the apiKey override.

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 ('send a test email for an existing campaign') and immediately frames the intent ('preview how it will look in recipients' inboxes'). The 'existing campaign' scope implicitly separates it from send_template_test and send_email, but no sibling is named, so the differentiation is inferred rather than stated.

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?

'Confirm the test address with the user first' is a concrete pre-call rule, and the SENDING_PAUSED remediation tells the agent what to do when refused. However, there is no guidance on when to pick this over send_template_test, send_email, or pre_send_review, so alternative routing is left to inference.

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