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

Annotations already signal read-only, open-world, idempotent, and non-destructive behavior. The description goes far beyond this by disclosing critical behavioral nuances: the distinction between `could_not_verify` (verification failure) and `unsupported` (no source coverage), the inclusion of `verification_error{stage,detail}`, the directive to never treat `could_not_verify` as evidence, and the internal routing logic. This is rich transparency that adds significant value.

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 single dense paragraph but every sentence contributes useful information, from example intents to error semantics to pipeline replacement. It could be slightly more structured with line breaks, but it is not redundant or padded. For a complex tool, this length is justifiable.

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 carries the burden of explaining return values: it lists all verdicts, mentions the literal value with `pipeworx://` citation, and explains reasoning. It also covers both categories of claims (company-financial and all other) and clarifies failure modes. Given the tool's complexity, the description is complete enough for an agent to know what to expect.

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 describes both parameters with 100% coverage, so the baseline is 3. The description adds extra semantic value for `tolerance_pct` by explaining its default behavior (implied by wording, capped at 5) and giving a concrete use case (1–2 for hallucination detection). The `claim` parameter is not further elaborated, but the schema examples cover it, so this exceeds the 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 clearly identifies the tool as a natural-language claim verifier, with explicit examples of user intents ("fact check", "verify the claim that…"). It distinguishes the tool from siblings by describing its internal routing (SEC EDGAR fast path for company financials, grounded pipeline for all other claims) and its unique verdict output, making it unmistakable what this tool does.

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 to use the tool "whenever the agent needs to check whether something a user said is factually correct," providing clear context. It also explains when the internal fast path applies vs. the general grounded pipeline, but it does not explicitly name alternative tools or state when NOT to use it, 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.