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

Despite annotations already indicating read-only, open-world, and idempotent behavior, the description adds significant context: the distinct processing paths, the full verdict enum, the critical distinction between 'could_not_verify' (check did not happen) and 'unsupported' (no source exists), and the callers note that 'could_not_verify' must not be shown as evidence. No contradiction with annotations; rather, it enriches them.

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 long but every sentence carries unique information: trigger phrases, usage scope, dual-path routing, return values, and an explicit caller warning. It is front-loaded with the most important usage cues and logically organized from purpose to details to caveats, with no 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?

For a 2-parameter tool with no output schema, the description covers all necessary context: what it does, when to use it, how parameters affect behavior (especially tolerance_pct), what verdicts are returned, and the crucial distinction between 'could_not_verify' and 'unsupported.' It also implies the output structure (value + citation + reasoning) sufficiently for an agent to invoke and interpret results.

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?

Schema coverage is 100%, so baseline is 3. The description adds extra nuance beyond the schema, particularly for tolerance_pct: 'Overrides the tolerance implied by the claim wording — set 1–2 for hallucination detection where any material error must be refuted' and explains the default cap of 5. Claim examples are also provided, adding practical usage value.

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 ('Is it true that…', 'fact check', 'verify the claim that…') and states a specific verb+resource: 'natural-language claim verification against authoritative sources.' It also distinguishes itself from siblings by noting it replaces 4–6 sequential calls, making its purpose unmistakable.

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 says 'Use whenever the agent needs to check whether something a user said is factually correct.' It also details two usage paths (SEC EDGAR for company-financial claims, grounded pipeline for all other factual claims), providing clear context on when each path applies. This goes beyond a generic statement and helps select the tool correctly.

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