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

The annotations already declare readOnly/idempotent/non-destructive, but the description adds crucial behavioral semantics: it enumerates the verdict values, distinguishes could_not_verify (check did not happen, with verification_error) from unsupported (no source exists), and explains that could_not_verify must not be presented as evidence. It also reveals the exact percent-delta math for financial claims and the grounded response with verbatim evidence, going well beyond the structured annotations.

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 dense paragraph but every sentence contributes: query triggers, usage rule, two routing paths, return contract, caller warnings, and efficiency justification. It is not padded, but the length is considerable; a bit more structure (e.g., bullets for the caller caveats) would make it even easier to parse, so it doesn't reach top score.

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 carries the full burden of explaining returns, and it does so thoroughly: verdicts, evidence citations, reasoning, error semantics for could_not_verify, and unsupported behavior. It also covers both routing paths and the tolerance parameter's behavior, so an agent has complete context to call the tool 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?

Both parameters are already fully described in the schema (100% coverage), and the description adds extra meaning by explaining that tolerance_pct overrides the wording-implied tolerance, defaults to a cap of 5, and suggests 1–2 for hallucination detection. This provides practical guidance beyond the schema, so the score is above baseline.

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 explicitly states the tool verifies natural-language factual claims ('fact check', 'verify the claim that…') and distinguishes itself from related tools by describing its two routing paths (SEC EDGAR for company-financial claims, grounded pipeline for others). It also positions it as replacing 4–6 sequential calls, clarifying the core purpose.

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 explicit direction: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also specifies the conditions for the two internal paths and notes that any other factual claim automatically falls through, making it clear this is the single tool for claim verification. While it doesn't explicitly name alternatives to avoid, the usage context is strong.

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