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

Beyond the readOnly/idempotent annotations, the description discloses critical behavioral details: the meaning of each verdict (could_not_verify means the check did not happen and must not be treated as evidence, unsupported means no source covered), the automatic fallback for non-financial claims, and the presence of verification_error. This added context is substantial and goes well beyond what annotations provide, making the tool's edge cases transparent.

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 well-structured and front-loaded with trigger examples, then usage, then return semantics, and an IMPORTANT caveat. Every section earns its place given the tool's complexity. It could be slightly tightened (e.g., the phrase 'routed to the right live source' is somewhat redundant), but overall it is appropriately sized relative to the tool's sophistication.

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?

With only 2 parameters and no output schema, the description carries the full burden of explaining return values. It thoroughly covers the verdict list, the value with citation, reasoning, and the distinct meanings of could_not_verify and unsupported. It also explains the routing logic for different claim types, making it complete for an AI 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 coverage is 100%, so the baseline is 3. The description adds meaningful semantics: it clarifies that tolerance_pct overrides the wording-implied tolerance, suggests values for hallucination detection (1-2), and notes the default cap at 5. It also gives realistic examples for the claim parameter. This enhances the schema without being redundant.

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 a specific verb ('validate claim') and resource (factual claims). It distinguishes itself from siblings by detailing the two verification paths (SEC EDGAR for financial, grounded pipeline for other) and by noting it replaces 4-6 sequential calls, making its scope and value explicit.

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 explicitly states when to use: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also gives examples of trigger phrases and claim types. However, it does not explicitly name alternative sibling tools or state when not to use this tool, only contrasts with the multi-step process it replaces. Thus it meets 'clear context' but lacks explicit exclusions or alternative tool names.

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