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

Annotations already declare readOnly/openWorld/idempotent/non-destructive. The description goes beyond those by explaining subtle behavioral semantics: 'could_not_verify' means the check did not happen and must not be shown as evidence, while 'unsupported' means no source covers the claim. It also discloses the routing logic and the presence of verification_error, which are critical for correct interpretation of 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 front-loaded with trigger phrases and a one-sentence purpose, then expands into routing and verdict semantics. Every sentence adds distinct information: trigger examples, usage, company-financial path, verdict list, error semantics, and efficiency benefit. It is long but appropriately so for a tool with this complexity, with no wasted words.

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?

The tool is complex (natural-language understanding, multiple backends, nuanced verdicts), and there is no output schema. The description compensates fully: it enumerates all six verdicts, explains what each means (especially could_not_verify vs unsupported), states the return includes grounded/structured value with citation, and describes the internal routing. This is sufficient for an agent to know exactly what to expect and how to act on results.

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%, so the baseline is 3. The description adds meaningful context beyond the schema: tolerance_pct's purpose ('Overrides the tolerance implied by the claim wording'), its use in hallucination detection ('set 1–2'), and its default behavior ('implied by wording, capped at 5'). This helps agents decide when and how to set the parameter. Slightly short of a 5 because the schema already provides solid 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 opens with concrete trigger phrases ('Is it true that…', 'fact check', 'verify the claim that…') and clearly states the tool performs natural-language claim verification against authoritative sources. It distinguishes itself from sibling search/research tools by focusing on verification with a verdict output and by naming the specific structured path (SEC EDGAR + XBRL) for company-financial claims.

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?

Explicitly states 'Use whenever the agent needs to check whether something a user said is factually correct.' It further separates usage by claim type: company-financial claims take the fast path, all others fall through to the grounded pipeline. It even notes that the tool replaces 4–6 sequential calls, giving a clear efficiency rationale. No exclusions are given, but the guidance is unambiguous and actionable.

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