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

The annotations already signal read-only, open-world, idempotent, non-destructive behavior. The description goes far beyond this by detailing the internal pipeline (SEC EDGAR/XBRL fast path vs. grounded pipeline), the exact return semantics with six verdict types, and the critical distinction between 'could_not_verify' (check did not happen) and 'unsupported' (no source exists). This adds substantial context that annotations do not provide.

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?

Despite being long, every sentence serves a purpose: trigger phrases, usage context, pipeline explanation, return values, and caller warnings. The structure is front-loaded with examples, then behavior, then nuances. No fluff—each sentence either adds usage guidance, describes behavior, or clarifies edge cases.

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?

For a complex verification tool with no output schema, the description fully covers return values (verdict list, actual value, citation, reasoning), the two processing paths, and the subtle error semantics. It explains both 'could_not_verify' and 'unsupported' explicitly, and mentions the tolerance behavior. No critical details are missing for an agent to invoke and interpret results 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?

The schema covers both parameters with descriptions, so baseline is 3. The description adds meaningful guidance, especially for tolerance_pct: it explains how to override the implied default, recommends 1–2 for hallucination detection, and notes the default cap of 5. This extra detail earns a 4, though the schema already carries most weight.

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 as verifying natural-language factual claims, using specific verbs like 'validate', 'verify', 'confirm or refute'. It distinguishes itself from generic search or Q&A tools by framing it as a claim-verification tool that returns a verdict and evidence, and explicitly mentions it replaces multi-step sequential calls.

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 states explicitly when to use the tool: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also gives concrete trigger examples and explains the two distinct pathways (company-financial vs. any other factual claim), and warns about the meaning of 'could_not_verify'. It positions itself as a replacement for a chain of calls, which provides implicit alternative guidance.

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