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

Annotations already mark readOnlyHint and idempotentHint, but the description adds essential behavioral nuance: could_not_verify means the check did not happen and must not be used as evidence, unsupported means no source covers the claim, and the return includes a verdict, citation, and reasoning. It also discloses distinct execution paths and the tolerance override mechanism, going well beyond annotation hints.

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 purpose and usage guidance, followed by pathway details and caller caveats. It is somewhat long but each sentence contributes useful information; minor redundancy exists in the grounded-pipeline phrase ('routed to the right live source, answered with verbatim evidence, then judged'), which could be tightened without losing meaning. Overall structure is logical and purpose-driven.

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 return values: verdict types, grounded/structured actual value with a pipeworx:// citation, and reasoning. It also covers error semantics (could_not_verify and unsupported) and notes the performance benefit of replacing multiple calls. For a tool of this complexity, the description is complete enough that an agent can invoke it 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 provides 100% coverage with clear descriptions for both claim and tolerance_pct, including examples, so the description does not need to add parameter-level detail. The description only implicitly references tolerance via 'exact percent-delta math' and 'tolerance implied by wording', which does not supplement the schema's existing clarity. Baseline 3 is appropriate since the schema is already comprehensive.

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 natural-language claim verification against authoritative sources, using explicit verbs like 'verify', 'fact check', and 'confirm or refute'. It distinguishes itself from siblings by explaining that it consolidates multiple pipeline steps (NL parsing → entity resolution → data lookup → comparison) into a single call, and by differentiating the handling of company-financial claims versus other factual 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 provides routing logic: company-financial claims go through SEC EDGAR + XBRL fast path, while any other claim falls through to the grounded pipeline, giving clear when-to-use guidance. The note about replacing 4–6 sequential calls frames this as the consolidated alternative, implicitly excluding older multi-step approaches.

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