Citable — prompts a domain is already cited for

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

Annotations already declare readOnlyHint=true and openWorldHint=true, but the description adds substantial behavioral context: it discloses the $0.25 USDC charge per call, notes 'Not charged on failure,' explains collapse of repeated observations with an `observations` count, and clarifies that outputs are observed rather than generated. This goes well beyond the annotations and provides useful operational detail.

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 compact yet information-dense, starting with the pricing note, then the core function, usage guidance, aggregation behavior, competitor use, and failure policy. Each sentence earns its place, and the structure front-loads the most critical details (pricing and purpose) before elaborating on specifics. Slightly longer than necessary but without fluff.

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 no output schema, the description compensates well by specifying the return fields: question, answer snippet, AI search volume, and exact URL cited. It also covers payment, failure handling, aggregation, and competitor use cases, making it a complete guide for an agent to call the tool correctly. Nothing essential is missing for a read-only lookup tool.

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 input schema already describes all three parameters with full coverage (100%). The description adds context about using the `domain` parameter to 'point at a competitor's domain,' which slightly enriches meaning, but it doesn't add significant depth to `limit` or `platform` beyond the schema. Since coverage is high, the baseline of 3 is appropriate.

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 identifies the tool's purpose: retrieving real questions that AI answer engines cite a domain for, with specific data elements (question, answer snippet, AI search volume, exact URL cited). It distinguishes from siblings by emphasizing 'observed prompts, never generated ones' and suggests pointing at competitor domains to get prompts they win, which sets it apart from suggestion-based tools like citable_keyword_suggest.

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 explicit usage guidance: 'use this to discover what to track instead of inventing them' and 'Point it at a competitor's domain to get the prompts they win and you do not.' This clarifies the intended scenario and differentiates from generated-prompt tools, though it does not explicitly name siblings or state when not to use it.

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