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

Annotations already mark readOnly, openWorld, and idempotent, but the description adds crucial behavioral nuance: it defines the meaning of could_not_verify (caller failure, not evidence), distinguishes it from unsupported (no source), and mentions the verification_error field. This prevents the agent from misusing ambiguous verdict states and clarifies what the tool does under the hood.

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 info-dense yet well-structured: it starts with natural-language triggers, explains the two processing paths, lists return values, and adds critical callers guidance about could_not_verify. Every sentence earns its place, and the structure is logical and front-loaded with the most essential usage signal.

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 specifies the verdict enum (confirmed, approximately_correct, refuted, inconclusive, unsupported, could_not_verify), the citation mechanism, and the difference between error and unsupported. It also mentions the replacement of 4–6 sequential calls, giving agents enough context 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 coverage is 100%, so the baseline is 3, but the description substantially enhances parameter understanding. It provides concrete examples for the claim parameter and explains that tolerance_pct overrides the claim wording's implied tolerance, with a specific recommendation (1–2) for hallucination detection. This goes well beyond the schema's description.

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 natural-language triggers ("Is it true that…", "fact check") and defines the tool as "natural-language claim verification against authoritative sources." This gives a specific verb (verify) and resource (claims) while clearly distinguishing it from sibling tools by noting it replaces 4–6 sequential calls, consolidating the purpose.

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 guidance states "Use whenever the agent needs to check whether something a user said is factually correct." It further divides usage into a structured SEC EDGAR/XBRL fast path for company-financial claims and a grounded pipeline for all other factual claims, offering clear context and the alternative of a single call versus a multi-step pipeline.

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