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

Beyond the annotations (readOnly, openWorld, idempotent), the description discloses critical behavioral nuances: the specific verdict vocabulary, the meaning of 'could_not_verify' (non-result, not evidence), the distinction from 'unsupported', the citation format (pipeworx://), and the tolerance cap. This is exactly the kind of operational detail an agent needs to correctly interpret results and avoid misleading the user.

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 and every sentence carries useful information. It front-loads with query examples and a clear 'Use whenever' call. Though lengthy, the structure logically flows from purpose → use → behavior → return values → important caveat → efficiency note. It earns its length given the complexity of claim verification.

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 compensates by detailing the return envelope: verdict list, actual value with citation, and reasoning. It also covers the two main claim categories, the tolerance mechanics, and the critical error semantics (could_not_verify vs. unsupported). For a tool of this complexity, this is a complete and self-contained specification.

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%, so the baseline is 3, but the description adds meaningful usage semantics beyond the schema: examples of well-formed claims, how tolerance_pct overrides wording-implied tolerance, the recommended range (1–2) for hallucination detection, and the default cap of 5. This enriches the agent's understanding of how to set and interpret both parameters.

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 example phrasings ('Is it true that…', 'fact check') and immediately states the core function: 'natural-language claim verification against authoritative sources.' It also differentiates the two execution paths (SEC EDGAR/XBRL fast path for company-financial claims vs. grounded pipeline for everything else), which distinguishes it from generic lookup tools and clarifies its specific scope.

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 says 'Use whenever the agent needs to check whether something a user said is factually correct,' which is clear guidance. It also gives an internal branch (company-financial vs. any other factual claim) and mentions the efficiency benefit of replacing multiple sequential calls. It does not explicitly name alternative tools to avoid, but the usage context is strong enough for an agent to decide correctly.

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