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

Annotations already declare readOnly, idempotent, and non-destructive, but the description goes well beyond that. It discloses the verdict taxonomy (including 'inconclusive' and 'could_not_verify'), explains critical semantic distinctions (could_not_verify vs unsupported), and reveals the verification_error{stage,detail} payload. This is rich behavioral context that helps the agent interpret results correctly and avoid misusing failure modes.

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 well-organized: trigger phrases, usage directive, two-path explanation, output details, caveats, and efficiency claim—each sentence earns its place. It is long enough to cover necessary complexity without bloat, and the most critical usage trigger is front-loaded.

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 carries the full burden of explaining return values and edge cases, and it succeeds. It specifies the verdict list, the evidence format (grounded value with pipeworx:// citation), and reasoning. It also clarifies failure semantics and distinguishes 'unsupported' (no source covers it) from 'could_not_verify' (check didn't happen). For a 2-parameter tool, this is exceptionally complete.

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 description coverage is 100%, so baseline is 3, but the description adds substantial meaning. For 'claim' it provides real examples; for 'tolerance_pct' it explains how it overrides the claim's implied tolerance, gives the default behavior (capped at 5), and offers a concrete use case (set 1–2 for hallucination detection). This is actionable guidance beyond the schema's mere type and presence.

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, then states a specific verb+resource: 'natural-language claim verification against authoritative sources.' It clearly differentiates from sibling research/Q&A tools by emphasizing deterministic verdicts and the two-pathway approach (SEC EDGAR vs grounded pipeline). It also positions itself as a replacement for 4–6 sequential calls, distinguishing it from generic lookup tools.

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?

Explicit when-to-use guidance is given: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also explains the two routing paths (company-financial vs. any other claim). However, it does not explicitly state when not to use it or name a specific alternative sibling tool, though it implies the alternative is the sequential pipeline it replaces.

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