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

Beyond the readOnly, openWorld, and idempotent annotations, the description discloses critical behavioral semantics: the exact verdict list (confirmed / approximately_correct / refuted / inconclusive / unsupported / could_not_verify), the meaning of 'could_not_verify' as a non-evidence error, and 'unsupported' as no-source coverage. It also warns about tolerance_pct behavior for hallucination detection and includes the return shape (value + citation + reasoning). This is exceptionally transparent.

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 delivers distinct value: trigger phrases, routing, return shape, error semantics, and performance benefit. It is front-loaded with the most critical usage signal first and contains no filler or tautology. A slight trim could improve conciseness, but the structure is logical and dense.

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 tool with no output schema, the description compensates fully by listing the return verdicts, the judgment logic, the citation requirement, and the meaning of error states. It explains both financial-claim fast path and generic grounded fallback, and clarifies that 'could_not_verify' is not evidence for or against. This gives an agent enough context to call the tool safely and interpret results accurately.

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 has 100% parameter coverage with detailed descriptions for both 'claim' and 'tolerance_pct', including examples, allowed range, override behavior, and default. The tool description adds little new parameter information—it mentions tolerance_pct briefly but mostly restates what the schema already contains. The schema carries the parameter-semantics weight, so a baseline 3 is appropriate.

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 natural-language trigger phrases ('Is it true that…', 'fact check') and unambiguously states it performs 'natural-language claim verification against authoritative sources.' It distinguishes itself from general lookup tools by describing a two-path routing (SEC EDGAR/XBRL for financials vs. grounded pipeline for all other facts) and notes it replaces 4–6 sequential calls, making its specific 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?

The description explicitly instructs 'Use whenever the agent needs to check whether something a user said is factually correct,' and it explains how different claim types route (financial vs. any other). However, it does not name alternative sibling tools or explicitly state when not to use it (e.g., for open-ended research), so it lacks the full 5-level 'when/when-not/alternatives' guidance.

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