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

Beyond the annotations (read-only, open-world, idempotent), the description reveals critical behavior: the distinction between structured and grounded paths, the verdict enum with specific meanings, and importantly the semantics of could_not_verify (check did not happen, not evidence) versus unsupported (no source coverage). This is rich behavioral context that annotations alone do not 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?

The description is long but densely packed with high-value information: trigger phrases, routing logic, output semantics, and error handling. Every sentence contributes, though its length is notable. It could be slightly tightened without losing substance, but overall it is well-structured and front-loaded.

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?

Given the tool's complexity, the absence of an output schema, and the need to correctly interpret verdicts, the description is exceptionally complete. It covers input, processing paths, return values, edge-case semantics, and the value proposition, leaving little ambiguity for an agent to select and invoke it 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%, but the description adds meaning: it gives concrete examples for 'claim' and explains how tolerance_pct overrides the implied tolerance, with specific guidance for hallucination detection (set 1–2%). This adds actionable detail well beyond the 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 clearly identifies the tool as natural-language claim verification against authoritative sources, with explicit trigger phrases ('fact check', 'verify the claim that'). It distinguishes itself from siblings by stating it replaces 4–6 sequential calls (NL parsing → entity resolution → data lookup → comparison), making its unique role unambiguous.

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?

It states exactly when to use: 'whenever the agent needs to check whether something a user said is factually correct.' It also differentiates the two execution paths (company-financial claims via SEC EDGAR + XBRL vs. any other factual claim via grounded pipeline), and explains it supersedes a multi-step approach, giving clear context versus alternative tools like resolve_entity or compare_entities.

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