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

Annotations already declare readOnly/openWorld/idempotent, but the description goes well beyond by disclosing crucial behavioral semantics: the distinction between could_not_verify (verification error, not evidence) and unsupported (no source coverage), the verdict taxonomy, and the fact that it replaces 4–6 sequential calls. This prevents misinterpretation of results and is genuinely useful for callers.

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 but every sentence earns its place: trigger phrases, usage guidance, routing logic, return values, and critical caveats. It front-loads the most important info and uses clear formatting, making it scannable despite its length.

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 there is no output schema, the description must convey return semantics, and it does thoroughly: verdicts, evidence citation, reasoning, and the very important warning about could_not_verify. It also explains how the tool handles different claim types, making it fully actionable for a complex verification task.

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% with solid parameter descriptions, so the baseline is 3. The description adds meaningful context: tolerance_pct overrides the claimed wording, its default and cap behavior, and examples of valid claims. This goes beyond schema descriptions, especially for tolerance semantics.

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 natural-language triggers ('Is it true that…', 'fact check', 'verify the claim that…'), then states the core function: natural-language claim verification against authoritative sources. It explicitly distinguishes the structured SEC EDGAR/XBRL fast path from the grounded pipeline for any other claim, clearly separating this tool from siblings.

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 gives an explicit directive: 'Use whenever the agent needs to check whether something a user said is factually correct,' and explains the two routing paths based on claim type. It doesn't name sibling tools as alternatives or say when to prefer deep_research, but the description strongly implies this is the single entry point for claim verification.

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