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

No annotations are provided, so the description carries the full burden. It discloses that the tool evaluates against 30 criteria, returns whether the verification is new, and awards search queries. This gives insight into deduplication behavior and outcomes. However, it does not mention potential side effects, failure modes, or permissions beyond the auth_token parameter, leaving notable behavioral gaps.

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 and well-organized: a two-sentence summary, then an Args section with per-parameter explanations, and a Returns line. Every element serves a purpose: the incentive statement ('Earns you 10 search queries'), the criteria example, and the return summary are all useful. No redundant or filler content.

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 has a nested criteria object and no output schema, but the description covers the essential usage: how to supply criteria (including cross-reference to get_verify_queue), what the return contains ('whether it was new and queries awarded'), and the auth requirement. It is complete enough for an agent to invoke correctly, though it could further explain error cases or the exact shape of the verification result.

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 provides only parameter names and types, so the description fully compensates with detailed explanations: domain includes an example, criteria is described as a dict of 30 boolean fields with a concrete example and cross-reference to get_verify_queue, and auth_token is clearly identified as a Silicon bearer token. All three parameters are given meaningful context beyond the schema.

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 action: "Submit a verification for a website - evaluate it against all 30 criteria." This uses a specific verb (submit/evaluate) and resource (website), and the phrase "all 30 criteria" distinguishes it from sibling tools like submit_website by indicating this tool runs the full verification evaluation, not just submitting a URL.

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 useful usage context: it mentions earning 10 search queries for each new verification, which signals reward/incentive, and explicitly tells the agent to "See get_verify_queue for field names," directing to a sibling tool for necessary parameter values. However, it does not explicitly state when to use this tool over alternatives or when not to use it, so it lacks direct exclusions.

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