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

Annotations declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, and the description adds important behavioral nuance beyond these: could_not_verify is explicitly defined as 'the check did not happen' and 'must not be shown as one,' while unsupported is distinguished as 'we looked and cover no source for it.' It also details the two routing paths (SEC EDGAR + XBRL fast path vs. grounded pipeline) and the return shape.

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 a one-liner, but every sentence earns its place: trigger phrases, routing logic, return contract, and a caller warning about could_not_verify are all compressed into a structured flow. The front-loaded natural-language examples immediately signal the tool's purpose, and the 'IMPORTANT for callers' section is a clear, high-value addition.

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?

Even without an output schema, the description fully enumerates return components 'verdict ... actual value with pipeworx:// citation, and reasoning' and explains the interpretation of could_not_verify and unsupported. It also covers both company-financial and general claims, the source-routing behavior, and the fallback semantics, making the tool's behavior sufficiently clear for an agent to invoke 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?

Schema description coverage is 100%, with rich descriptions for both `claim` and `tolerance_pct` already including examples and threshold guidance. The description adds general context about 'exact percent-delta math' but does not provide additional parameter-specific meaning beyond what the schema offers, so baseline 3 is appropriate.

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 a specific verb+resource pairing: 'natural-language claim verification against authoritative sources' and explicitly states the tool checks 'whether something a user said is factually correct.' It further distinguishes itself by listing the returned verdict types and noting it replaces 4–6 sequential steps, making it clearly distinct from 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 includes an explicit trigger: 'Use whenever the agent needs to check whether something a user said is factually correct,' and it differentiates between company-financial claims and other factual claims via routing. It does not name alternative sibling tools or provide formal when-not-to-use conditions, but the context is clear enough to guide selection.

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