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

Beyond the annotations (readOnly, idempotent, non-destructive), the description richly discloses behavioral nuances: the distinction between could_not_verify and unsupported, the presence of verification_error{stage,detail}, and the instruction that could_not_verify must not be treated as evidence. It also reveals the underlying pipeline architecture (structured fast path vs. grounded fallback) and output citation format, providing substantial value beyond structured fields.

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 longer than typical, but every sentence contributes meaningful information: example triggers, routing logic, output types, and critical caller guidance. It is structured with semicolons and a clear 'IMPORTANT for callers' note, making it dense but scannable. The length is justified by the complexity, so it earns a 4 rather than a 3.

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 covers the return contract: verdict enum values, actual value with pipeworx: citation, reasoning, and error semantics. It also explains the pipeline alternative to 4-6 sequential calls, addresses edge cases (could_not_verify vs unsupported), and provides enough about inputs and behavior to be independently actionable. The tool's complexity is high, and the description addresses all key dimensions.

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 schema already fully documents `claim` and `tolerance_pct` with examples and semantics. The description adds no parameter-level meaning beyond what the schema provides, though it does mention tolerance implication and hallucination detection in the schema itself. It appropriately doesn't repeat schema details but also adds nothing extra for the parameters.

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 states a specific verb and resource: 'natural-language claim verification against authoritative sources'. It clearly distinguishes the tool from siblings by defining its exact function (claim verification) and listing concrete example phrasings. It also separates financial claims (SEC EDGAR/XBRL) from other grounded claims, making the purpose unmistakable and unique among the sibling 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?

The description explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct' and explains the two routing paths (financial vs. other claims). It doesn't explicitly name alternatives or when-not-to-use for open-ended research, so it stops short of a full 5, but the context is clear and actionable.

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