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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description goes well beyond this by explaining the two verification paths, the exact verdicts, and the critical nuance that could_not_verify means the check did not happen and must not be treated as evidence. This adds substantial behavioral context beyond structured metadata.

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 earns its place: it front-loads user intents, explains the two pipelines, lists verdicts, highlights the error semantics, and ends with the benefit of replacing 4–6 calls. The structure is clear with an important callout, though slightly verbose for a tool with only 2 parameters.

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?

Despite no output schema, the description fully defines the return values (six verdicts, actual value with citation, reasoning) and edge-case behaviors (could_not_verify vs unsupported). For a 2-parameter tool this is thorough and leaves no obvious gaps in what the agent needs to know.

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 covers both parameters at 100%, but the description enriches them by mentioning 'exact percent-delta math' for structured claims and tying tolerance_pct to hallucination detection (e.g., 'set 1–2 for hallucination detection'). This explains how the parameters affect the grading process rather than just their syntax.

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 natural-language user phrasings ('Is it true that…'), then states a specific verb+resource: 'natural-language claim verification against authoritative sources.' It distinguishes itself from sibling research/QA tools by framing itself as a verdict-returning claim checker that replaces 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?

Explicitly tells the agent when to use it: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also provides a decision rule between the SEC EDGAR fast path for company-financial claims and the grounded pipeline for other claims. No explicit alternatives are named, but the context is clear and excludes other use cases.

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