preview_campaign

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

The description explains the validate_only mechanism, confirms nothing is written, and enumerates the return payload (rendered plan, errors, confirm_token). This adds meaningful context beyond the readOnlyHint and openWorldHint annotations. It doesn't cover token expiry or authentication details, but those are less critical for safe invocation.

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 two sentences with no filler. The critical dry-run and side-effect-free facts are front-loaded, the return values are listed, and the user-facing instruction is included. Every phrase 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 one-parameter tool with an output schema and readOnlyHint annotation, the description covers what the tool does, what it returns, and the required relationship to create_campaign. The only shortcoming is the lack of explicit parameter-level guidance, but the rich input schema compensates for that. Overall it gives an agent enough to invoke it correctly and understand the expected flow.

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?

The single `spec` parameter has no description in the schema (0% coverage at the top level), and the tool description doesn't explain its structure. However, the nested CampaignSpec schema is extensively self-documented with descriptions for fields like customer_id, daily_budget, and final_url. The description adds the high-level 'campaign spec' framing but no field-level guidance, so the schema carries most of the burden.

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 states a specific verb ('Dry-run'), a specific resource ('campaign spec'), and the key outcome ('validate_only so nothing is written'). It also distinguishes itself from create_campaign by returning a confirm_token to pass to that tool. No ambiguity about what this tool does.

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?

It gives an explicit, mandatory usage rule: 'Always call this before create_campaign; show the plan to the user.' This tells the agent exactly when to invoke this tool and names the relevant sibling as the follow-up. It also implies when not to use it (when ready to write a campaign).

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