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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description adds valuable behavioral context: the distinction between the two verification paths, the specific verdict values returned, the critical meaning of could_not_verify (that it does not constitute evidence), and the behavior for unsupported claims. This far exceeds the structured data already provided.

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 a moderately long paragraph of seven sentences, but every sentence carries important information: examples, usage triggers, routing logic, return types, error semantics, and the consolidation benefit. It is well-structured with semicolons and em-dashes that aid readability, though it could be slightly trimmed without losing value.

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?

For a tool with this complexity, the description is remarkably complete. It explains both processing paths, the full set of verdicts, the meaning of error states, citation format, and the problem it solves. The schema and annotations already provide additional context, and there is no output schema, so the description carries the full burden of explaining return values—which it does thoroughly.

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?

The input schema has 100% coverage and each parameter already has a detailed description, including the default behavior and usage guidance for tolerance_pct. The tool description does not add meaningful information about the parameters beyond what the schema provides, so the baseline 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 states the tool's purpose: natural-language claim verification against authoritative sources. It provides multiple example phrasings, distinguishes it from siblings by describing the SEC EDGAR fast path for company-financial claims and the grounded pipeline for other claims, and mentions that it replaces 4–6 sequential calls. This makes the tool's function specific and easily distinguishable.

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 provides clear when-to-use guidance. It also explains the routing logic for different claim types. However, it does not name alternative tools or provide when-not-to-use exclusions, so it falls short of the highest level of guidance.

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