Create a marketing campaign

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

The description discloses that recipients are validated and deduplicated, and that voiceLint conditionally scores body copy as a warn-only attachment. Annotations (readOnlyHint=false) are consistent. No destructive behavior is mentioned, but the tool creates a resource, so behavioral transparency is adequate.

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?

The description is three sentences covering main action, recipient processing, and a conditional feature. It is front-loaded with the core purpose. No unnecessary words, but could be slightly more structured.

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?

No output schema exists, but the description mentions returns: campaign + stats. However, it lacks details on stats content, error conditions, or constraints like duplicate names. Given the tool's complexity (6 params, 3 required), it is minimally complete but not exhaustive.

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 33% with descriptions only for batchSize and recipients. The description adds context about recipient validation and batch size computation, but does not explain required parameters like project and name. For a 6-param tool, the description adds marginal value beyond the schema.

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?

The description clearly states the tool creates a marketing campaign with recipient list and batch size. It specifies recipients are validated and deduplicated, and that sending is handled separately. It also mentions a conditional voiceLint feature. This distinguishes it from sibling tools like list_campaigns and get_campaign.

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 description implies the tool is for campaign setup, leaving sending to user/connector. However, it does not explicitly state when to use this tool versus alternatives or provide exclusions. There is no direct comparison with other campaign-related tools.

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