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

Beyond the read-only/idempotent annotations, the description discloses critical behavioral details: the two execution paths (SEC EDGAR/XBRL fast path vs. grounded pipeline), the full set of verdicts, and the subtle difference between could_not_verify (check failed, not evidence) and unsupported (no source found). It also warns callers not to treat could_not_verify as evidence, which is essential for correct use.

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?

Though the description is long, every sentence carries important information: trigger phrases, usage context, internal routing, return values, error semantics, and performance benefits. It is well-organized, front-loaded with user intents, and uses clear formatting (e.g., bolded verdicts, the "IMPORTANT" callout) to improve readability without waste.

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 explains what the tool returns (verdict, actual value with citation, reasoning) and clarifies ambiguous outcomes (could_not_verify vs. unsupported). It also covers edge cases like verification_error and the automation of a multi-step workflow, making it sufficiently complete for an agent to invoke and interpret results 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?

The input schema already provides thorough descriptions for both parameters, including examples and default behavior for tolerance_pct. The tool description itself does not add much parameter-specific meaning; it only indirectly references tolerance via "exact percent-delta math." Since schema coverage is 100%, a baseline of 3 is appropriate and no significant enrichment is added.

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 invocation patterns ("Is it true that…", "fact check", etc.) and defines the tool as "natural-language claim verification against authoritative sources." It clearly distinguishes itself from general Q&A tools by focusing on validating factual claims and even specifies a dual pipeline for financial vs. other claims, plus the exact verdict categories returned.

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 states explicitly "Use whenever the agent needs to check whether something a user said is factually correct," which sets a clear trigger. It also differentiates between company-financial claims and other factual claims, but it does not name alternative tools or give explicit "when not to use" guidance, so it falls short of a 5.

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