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

Beyond the annotations (read-only, idempotent), the description discloses crucial behavioral nuances: the distinction between 'could_not_verify' (check did not happen) and 'unsupported' (no source exists), the inclusion of verification_error details, and the explicit warning not to treat could_not_verify as evidence against the claim. It also explains the structured vs. grounded fallback paths.

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, the description is densely packed with high-value information, organized in a logical flow: user intent, use cases, domain routing, output description, error semantics, and efficiency benefit. No sentence is wasteful; the structure aids comprehension rather than hindering it.

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 description fully equips an agent to use this tool correctly for a complex verification task. It covers input examples, return values (verdict enum, actual value with citation, reasoning), error handling (verification_error), and the difference between failure and unsupported. With no output schema present, the description carries this burden entirely and succeeds.

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 good descriptions, and the description adds meaningful context for tolerance_pct: it can override implied wording, is suggested for hallucination detection, and has a capped default of 5. This goes beyond the schema and helps the agent choose correct values.

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 starts with explicit natural-language examples ('Is it true that…', 'fact check') and names the exact function: natural-language claim verification against authoritative sources. It also distinguishes itself from sibling tools by noting it consolidates multiple sequential calls into one operation, making its scope and value clear.

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?

It explicitly states when to use the tool ('Use whenever the agent needs to check whether something a user said is factually correct') and even separates company-financial claims from other factual claims, explaining the routing logic. However, it does not name specific alternative tools or state when not to use it, leaving some ambiguity for an agent comparing siblings.

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