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

Annotations already mark it read-only, open-world, idempotent, and non-destructive. The description adds crucial behavioral details beyond that: it distinguishes could_not_verify (check didn't happen, must not be shown as evidence) from unsupported (no source covers it), explains the structured vs. grounded routing, and notes it returns verdict, actual value, citation, and reasoning. This goes well beyond the annotation hints.

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 long but information-dense; it packs trigger phrases, purpose, internal paths, return values, error semantics, and an efficiency note into a single paragraph. It's structured with semicolons and dashes for readability. While not as terse as possible, every sentence earns its place given the tool's nuances.

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?

Given the schema covers both parameters and no output schema exists, the description nonetheless enumerates the six possible verdict values, explains the meaning of the two ambiguous ones (could_not_verify, unsupported), and hints at the comparison math (exact percent-delta). It also positions the tool as replacing a multi-step pipeline, giving the agent a full picture of what to expect.

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 already documents both parameters with examples (e.g., 'Apple's FY2024 revenue was $400 billion') and the 0.5–50 range for tolerance_pct. The description adds semantic value by explaining that tolerance_pct overrides the claim-implied tolerance, recommends 1–2% for hallucination detection, and notes a default cap of 5%. For 'claim', the description reinforces the natural-language nature but doesn't add new facts.

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 defines the tool as natural-language claim verification against authoritative sources, with explicit trigger phrases ('fact check', 'verify the claim that…') and the statement 'Use whenever the agent needs to check whether something a user said is factually correct.' It also differentiates the financial-claims fast path from the general grounded pipeline, and notes it replaces 4–6 sequential calls, distinguishing it from siblings.

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 gives an explicit usage directive: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also explains the two internal pathways for financial vs. other claims, which implies the appropriate context. However, it does not explicitly name alternatives or state when not to use the tool, so it stops short of full-guidance.

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