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

With no annotations, the description discloses that the output is a leading-signal prediction, not a guarantee, and not an official action, as well as time frame ('weeks early'). It sets appropriate expectations about the non-deterministic nature of predictions, though it does not cover error handling or output structure.

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 moderately sized but front-loaded with a clear purpose statement and uses each sentence to convey unique information. It avoids redundancy and even includes a caveat about non-guarantee 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?

Given only 2 parameters, no output schema, and no annotations, the description covers the tool's purpose, the meaning of each domain, entity type, and the qualitative nature of the output. It also includes an important limitation note, making it complete for practical use.

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?

Adds significant meaning beyond the schema: domain descriptions explain each vertical's focus (e.g., 'recall' from complaint velocity, 'bio' from NIH→trial→SEC chain) and entity examples (Tesla Model Y, Moderna). Schema only provides minimal descriptions, so this enrichment is valuable.

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 it returns predictions about entities using leading signals, explicitly listing four verticals (recall, bio, recompete, ma) with examples. It distinguishes from sibling 'list_domains' by describing prediction behavior rather than just listing domains.

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?

Provides context by explaining how 'domain' selects the vertical and gives examples of entity names, but does not explicitly contrast with when to use 'list_domains' or state exclusions. It implies usage scenarios through the domain descriptions.

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