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

The description directly contradicts the openWorldHint annotation. openWorldHint=true suggests the tool may access external data or perform outbound actions, but the description explicitly states 'no external research or outbound actions.' This is a clear contradiction. Additionally, the description mentions payment authorization and side effects, but the contradiction takes precedence per the rubric, warranting a score of 1.

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 and efficiently front-loads the core purpose. It includes essential operational details (price, payment authorization) without verbosity. While it could be slightly more structured, it is appropriately sized and avoids redundancy. A minor deduction for the repetition of 'no external research or outbound actions' in close proximity, but overall it's concise.

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?

The tool involves payment, multiple parameters including signatures, and a nested input object, yet the description omits critical details: how to structure the input, what the draft format looks like, what the signature fields mean, and the payment flow. Without an output schema or parameter explanations, an agent would struggle to correctly invoke the tool. The contradiction with annotations further undermines completeness.

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 0%. The description does not explain any of the five parameters, including the nested input object (brief, source_text, audience) or the signature/expiry fields. With such low coverage, the description must compensate, but it provides no parameter-level guidance. The only tangential mention is price/payment, which doesn't clarify parameter semantics.

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's function: 'Produce value propositions mapping supplied capabilities to business outcomes and supporting evidence.' It specifies a concrete deliverable (value propositions) and the input source (buyer-supplied capabilities). This distinguishes it from sibling content-generation tools like ad copy or blog drafts, and the constraint 'Uses buyer-supplied information only' further clarifies scope.

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 provides clear usage context: it uses buyer-supplied information, performs no external research, and returns a draft for human review. This implies when to use it (when you have internal capabilities and want value propositions) and when not (if external research is needed), though it doesn't explicitly name alternatives. It also notes pricing and payment requirements, which are important operational conditions.

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