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

Beyond the readOnly/idempotent annotations, the description discloses important behavioral traits: the SEC EDGAR + XBRL fast path for financial claims, the grounded pipeline fallback for other claims, and the return structure (verdict, actual value with pipeworx:// citation, reasoning). It also explains the critical distinction between could_not_verify (no evidence for/against) and unsupported (no source), which is essential for correct caller interpretation.

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 dense but every sentence earns its place: trigger phrases, usage guidance, routing behavior, return values, error semantics, and efficiency benefits. It is front-loaded with concrete examples and organized logically, with no filler or redundancy.

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 lacking an output schema, the description fully covers return values (verdict types, actual value, citation, reasoning) and explains edge cases like could_not_verify and unsupported. It also sets expectations about replacing sequential calls, making it complete for an AI agent to select and invoke the tool correctly.

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% and both parameters (claim, tolerance_pct) already have detailed descriptions, including examples, default behavior, and suggested values. The tool description adds only minimal additional context (e.g., 'exact percent-delta math') and does not materially enhance parameter understanding beyond the schema, so the baseline score of 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 clearly identifies the tool as natural-language claim verification, with explicit trigger phrases ('fact check', 'verify the claim that...') and a specific resource: checking factual correctness against authoritative sources. It distinguishes itself from sibling tools by focusing on verifying claims rather than general Q&A or research, and it clearly states the scope of what the tool does.

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 provides explicit guidance: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also explains the internal routing for company-financial claims versus any other factual claim, and notes that it replaces 4–6 sequential calls, giving clear context for when to invoke. However, it does not explicitly name alternative tools or state when NOT to use it, so it stops short of full when-not guidance.

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