Create campaign

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

Annotations already disclose non-read-only, non-idempotent, non-destructive, open-world. The description adds genuinely useful behavior beyond that: the call only produces a draft and never sends, and delivery requires a separate confirmed step. It does not cover auth/domain-verification prerequisites or side effects like audience-count freezing, so a 4 rather than 5.

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?

Bold-labeled sections (Purpose, Not for, Returns, Use when, Note) are front-loaded and scannable. Every line earns its place, with no redundant restatement of the name or schema.

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?

With 11 parameters and no output schema, the description still names the return (created draft with id) and explains the audience-branch complexity. It leaves the non-audience parameters undocumented in prose, but the schema descriptions and enum labels cover much of that, making the definition nearly complete.

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 only 45%, so the description carries extra burden. It usefully explains the audienceType branches (ALL/SEGMENT/FILTERED, segmentId for SEGMENT, inline audienceCondition for FILTERED), which is the hardest part of the schema, but adds nothing for name/subject/body/type/description/replyTo/fromName. Partial compensation for the coverage gap lands at 3.

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+resource ('Create a campaign as a draft') with an explicit scope boundary ('It is never sent by this call'). It names the sibling it is not (plunk_send_transactional) and contrasts campaign vs one-off message, so an agent can distinguish it from the many other campaign siblings.

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?

Explicit 'Not for' clause routes the transactional case to plunk_send_transactional, and 'Use when' gives the composing-a-newsletter context. It also flags that sending is a separate, confirmed step, closing the obvious follow-up ambiguity.

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