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

Annotations already mark readOnly, idempotent, and non-destructive. The description goes beyond by disclosing the full verdict vocabulary, the distinction between 'could_not_verify' (pipeline failure, not evidence) and 'unsupported' (no source coverage), and the presence of verification_error fields. This is exactly the kind of behavioral nuance that structured annotations cannot convey.

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?

Though long, every sentence earns its place: purpose, routing logic, return contract, verdict semantics, and performance benefit. The front-loaded examples and explicit callout for 'could_not_verify' make the critical usage caveat impossible to miss. It is dense but well organized.

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 specifies return values: verdict list, actual value with citation, reasoning, and error details. It covers failure modes and interpretation rules. For a 2-parameter tool with rich defensive semantics, this is complete.

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% with meaningful descriptions for both parameters. The description adds extra semantic value beyond the schema: it explains how tolerance_pct overrides claim-wording defaults, caps at 5, and recommends 1–2 for hallucination detection. This helps the agent set parameters appropriately without requiring extra knowledge.

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 concrete natural-language invocation examples and a clear verb-resource pairing ('validate claim', 'fact check', 'verify the claim'). It explicitly states what the tool does — verify factual claims against authoritative sources — and differentiates itself from sibling research/entity tools by framing it as a single call replacing 4–6 sequential steps.

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 states when to use it: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also gives a decision rule for company-financial claims (SEC EDGAR/XBRL fast path) versus any other factual claim (grounded pipeline), effectively telling the agent when to prefer this tool over generic research or entity-resolution tools.

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