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

Beyond the annotations (read-only, idempotent, etc.), the description discloses crucial behaviors: the use of a structured SEC EDGAR + XBRL fast path with exact percent-delta math, automatic fallback to a grounded pipeline for other claims, the specific verdict types returned, the 'pipeworx:// citation', and the critical distinction between 'could_not_verify' (check did not happen) and 'unsupported' (no source). It also warns callers not to display 'could_not_verify' as evidence. This is far beyond what annotations provide.

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?

Although the description is long, it is efficiently packed with actionable information. It is front-loaded with trigger phrases and the core purpose, then logically expands into routing, outputs, verdict semantics, and a caller warning. Every sentence earns its place; no fluff 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?

With no output schema, the description fully compensates by detailing the return verdicts (confirmed, approximately_correct, refuted, inconclusive, unsupported, could_not_verify), the grounded/structured actual value with citation, and the reasoning. It also covers error semantics for 'could_not_verify' with verification_error{stage,detail}. For a tool of this complexity, the description 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%, and the description adds substantial semantic value. 'claim' is explained with natural-language examples and format expectations; 'tolerance_pct' is given a full behavioral explanation (overrides implied tolerance, range, default cap of 5, and use case for hallucination detection). This goes well beyond the bare schema descriptions.

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 uses a specific verb ('validate', 'check', 'verify') and clearly identifies the resource (factual claims against authoritative sources). It is explicitly distinguished from sibling tools by focusing on natural-language claim verification, and it provides concrete trigger phrase examples making the purpose unmistakable.

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 states when to use it: 'Use whenever the agent needs to check whether something a user said is factually correct.' It further explains the two distinct routing paths (SEC EDGAR for company-financial claims, grounded pipeline otherwise) and emphasizes that 'could_not_verify' means the check did not happen and should not be treated as evidence. It also positions the tool as a replacement for 4–6 sequential calls, giving clear operational guidance.

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