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

Despite strong annotations (readOnly, idempotent, openWorld, non-destructive), the description adds critical behavioral nuance: it explains the meaning of each verdict, especially the distinction between could_not_verify (check failed, no evidence) and unsupported (no source found). It also discloses that evidence includes pipeworx:// citations and that tolerance can be overridden for hallucination detection—none of this is in the annotations.

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 longer than average but every sentence earns its place. It starts with concrete examples, then explains the two paths (structured vs. grounded), lists verdicts, clarifies error semantics, and ends with the value proposition. No filler or repetition—it is dense but highly scannable.

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 covers return values (verdict, actual value, citation, reasoning) and error handling (verification_error with stage and detail). It also explains edge cases (could_not_verify vs unsupported) and positions the tool's efficiency gain. Given the tool's complexity, this is a complete and self-sufficient 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?

Schema already covers 100% of parameters with descriptive text. The description goes further by explaining the tolerance_pct default behavior ('capped at 5') and how to use it (1–2 for hallucination detection), and describes the internal math ('exact percent-delta math') for financial claims, adding context beyond the schema's static definitions.

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 and a clear verb+resource: 'natural-language claim verification against authoritative sources.' It distinguishes this from sibling tools by stating it 'Replaces 4–6 sequential calls' and covers both structured financial verification and grounded fallback for all other claims.

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?

Provides explicit guidance: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also explains routing logic (SEC EDGAR for financial claims, grounded pipeline otherwise) and gives a clear exclusion: could_not_verify must not be treated as evidence. This is more specific than typical 'use when' guidance.

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