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

The description adds rich behavior beyond the readOnly/openWorld/idempotent annotations: it explains verdict semantics, notably that could_not_verify means the check did not happen and must not be shown as evidence, and that unsupported means no source was found. It also discloses the routing behavior and return contents (verdict, value with citation, reasoning), which is valuable for callers.

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 a single dense paragraph and is longer than minimal, but every sentence carries substantive information—trigger phrases, routing logic, verdict meanings, and a caller-facing warning. It is front-loaded with purpose and ends with a useful note about replacing multiple calls, so it is efficient despite its length.

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 enumerates the possible verdicts, explains the meaning of could_not_verify and unsupported, and describes the returned components (value, citation, reasoning). It also covers both input types and the internal fallback behavior, making it sufficiently complete for a tool of this complexity.

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 description does not add parameter-specific detail about claim or tolerance_pct beyond what the schema already provides; the phrase 'exact percent-delta math' hints at the comparison mechanism but does not elaborate on tolerance semantics. The schema's own descriptions are sufficiently detailed.

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 states the tool's purpose: natural-language claim verification against authoritative sources, with trigger phrases like 'fact check' and 'verify the claim that…'. It distinguishes itself by explaining the structured SEC/XBRL fast path for company-financial claims versus a general grounded pipeline for all other factual claims, making it distinct from sibling Q&A 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?

It explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct' and explains the two routing paths (company-financial vs. any other factual claim). It also warns about could_not_verify not being evidence, but it does not name alternative sibling tools or explicitly state when not to use it, so it falls slightly short of full alternative guidance.

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