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

The description contradicts the annotations: openWorldHint=true implies the tool may access external world information, while the description explicitly says 'Uses buyer-supplied information only; no external research or outbound actions.' This is a direct inconsistency. Additionally, destructiveHint=true is not addressed beyond mentioning payment authorization, leaving destructive side effects undisclosed.

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?

Four sentences, each earning its place: the core function, the inference-only caveat, the input/no-research constraint, and the deliverable/pricing/authorization note. The most important information is front-loaded.

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?

Despite covering function, inference nature, output as a draft, and payment, the description omits critical call details: required input structure, how payment authorization is provided, and any handling of signature or expiry fields. With no output schema and a nested input object, an agent still lacks enough information to invoke the tool correctly.

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%, so the description must compensate, but it only vaguely refers to 'supplied keywords.' It does not explain the required nested input object with 'brief' and 'source_text', nor the optional fields like 'payment_signature', 'idempotency_key', 'result_expires', or 'result_signature'. The description adds minimal meaning beyond the schema's bare field names.

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 and resource: 'Classify supplied keywords by likely intent with rationale and uncertainty.' It also distinguishes itself from live search data, making its scope clear even among many siblings. The deliverable ('a draft for human review') further clarifies what the tool produces.

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 gives clear context for when to use the tool: when supplied keywords need intent classification. It also provides exclusions ('not live search data', 'no external research or outbound actions'), which helps an agent avoid misusing it for research-like tasks. It does not explicitly name alternative tools, but the usage context is strong enough for selection.

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