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

Beyond the read-only/idempotent annotations, the description discloses the full verdict taxonomy, the critical meaning of could_not_verify (check did not happen, must not be used as evidence), and the distinction between unsupported and could_not_verify. It also reveals the internal routing logic and the fact that it replaces multiple sequential calls—transparency that annotations alone 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?

The description is front-loaded with trigger phrases and a one-line purpose, then systematically covers behavior, return values, and an explicit caller warning. Every sentence adds distinct value; no filler. The length is justified by the complexity of the tool.

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 fully explains return verdicts, citation format, and reasoning. It covers edge cases (could_not_verify, unsupported), gives domain-specific routing details, and even mentions the performance benefit of replacing multiple calls. For a tool of this complexity, this is a complete and self-contained description.

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?

While the schema covers both parameters 100%, the description adds significant context: it explains that tolerance_pct overrides claim-implied tolerance, gives a concrete use case (1-2% for hallucination detection), and clarifies the default cap at 5%. The claim parameter is also enriched with examples from the description's opening. This goes well 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 opens with explicit trigger phrases ('fact check', 'verify the claim that…') and defines the tool as natural-language claim verification. It clearly distinguishes from siblings by focusing on fact-checking against authoritative sources, and even mentions replacing sequential calls, positioning it as a composite verification tool.

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 explicitly states 'Use whenever the agent needs to check whether something a user said is factually correct.' It also delineates the two processing paths (company-financial vs. any other claim), providing clear context on when each applies and how the tool behaves differently. This gives an agent actionable guidance on invocation.

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