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

Annotations already declare read-only, open-world, idempotent, and non-destructive hints, and the description adds critical non-obvious behaviors: the full verdict enum, the distinction between 'could_not_verify' and 'unsupported' (including how callers must present them), the citation format (pipeworx://), and the two execution paths (SEC EDGAR/XBRL vs. grounded pipeline). This goes far beyond the annotations and materially changes how an agent should interpret and handle results.

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 long but every sentence earns its place. It front-loads the purpose with user phrasings, then provides usage, routing, return value details, and important caller warnings. The structure is logical, though slightly dense; it could be tightened without losing content, but it's not excessively verbose for the complexity it covers.

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 carries the full burden of explaining return semantics. It lists all verdicts, describes the actual-value + citation + reasoning output, and explicitly defines error states ('could_not_verify' vs 'unsupported') with guidance on how to present them. It also accounts for both structured and grounded pipelines, making the tool's behavior fully comprehensible to an agent without external documentation.

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 have descriptive texts. The description adds extra semantic value by explaining that tolerance_pct overrides the wording-implied tolerance, gives a concrete use case ('set 1–2 for hallucination detection'), and clarifies the claim format with examples. This elevates it above the bare schema baseline.

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'), then names the resource: 'natural-language claim verification against authoritative sources.' It clearly distinguishes itself from siblings by focusing on fact-checking and claim verification, and even notes it replaces 4–6 sequential calls, making its unique role explicit.

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 gives a clear trigger: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also explains routing for company-financial claims versus other factual claims, which is an important when-to-use nuance. It doesn't explicitly name sibling tools to avoid or say 'don't use this for open-ended research,' but the guidance is strong and can be inferred.

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