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

No annotations are provided, so the description must carry the full behavioral burden. It clarifies that the tool does not bill automatically and mentions geo_mismatch rejection. However, it does not disclose other behavioral traits like authentication requirements, rate limits, or what happens if the campaign is invalid or expired.

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 one long 4-sentence paragraph. It packs important information but is not front-loaded with the most critical action. The first sentence puts the agent role in brackets and uses jargon ('cpr/cpia/cppromo/cpd units') that could be streamlined. It earns its keep but could be 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?

Given there is no output schema, the description does not explain what the return payload looks like (e.g., fields like code, percent_off, valid_until). For a fetch tool, the response format is critical. The description mentions some payload fields in passing but does not describe the structure. The sibling tools are complex, and the description adequately distinguishes this tool from report_* tools, but completeness is limited by the missing output information.

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 67%, with two parameters (geo, country) already having descriptions. The description adds context that country is required for geo-safe serve and that server rejects on mismatch, but it does not add meaning for campaignId beyond what the schema provides. It also explains the alias relationship between geo and country.

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 that the tool fetches creative and coupon/promo payload for a campaign. It specifies 'agent-directed pull' and the context in which the data is injected (recommendation/decision context). This differentiates it from simply delivering an ad, though the specific verb 'deliver' in the name is somewhat inconsistent with the actual action ('fetch').

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 explicitly states that the tool does not bill by itself and directs the agent to use report_impression or report_conversion after acting on the payload. It also explains when to pass the country parameter for geo-safe serve and what happens on mismatch. However, it does not explicitly say when NOT to use this tool versus alternatives like request_platform_demand.

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