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

Annotations already declare the tool read-only, idempotent, and open-world. Beyond this, the description reveals two internal pipelines (SEC EDGAR/XBRL fast path vs. grounded pipeline), explains the verdict meanings, and adds a critical caveat that could_not_verify indicates a failure and must not be presented as evidence. This significantly exceeds the annotation-only picture and covers 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-structured: trigger phrases, core purpose, routing details, output summary, and cautions. Every sentence earns its place, though it is wordier than strictly necessary. It is front-loaded with purpose and usage, but the length prevents a perfect score.

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?

Despite lacking an output schema, the description fully specifies the six possible verdicts, the return content (grounded/structured value, citation, reasoning), and the special error object for could_not_verify. It also explains the scope of unsupported and the replacement of a sequential pipeline, making the tool's behavior clear and self-contained.

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%, and both parameters already have thorough descriptions. The main description's reference to 'exact percent-delta math' and implied tolerance adds some context, but it largely echoes the schema and does not introduce new parameter-level meaning. Baseline of 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 explicit user phrasings and identifies the tool as 'natural-language claim verification against authoritative sources.' It clearly specifies the resource (claims) and the action (verify), enumerates possible verdicts, and differentiates internal routing (financial vs. other claims), making it distinct from generic search or research 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?

Provides an explicit usage directive: 'Use whenever the agent needs to check whether something a user said is factually correct,' with multiple query examples. It also clarifies the distinction between could_not_verify and unsupported, guiding post-invocation behavior. However, it does not name sibling tools or explicitly state when to choose an alternative, 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.