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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint), the description discloses critical behavioral nuances: the exact meaning of 'could_not_verify' (check did not happen, not evidence, must not be shown as one), 'unsupported' semantics, and error structure (verification_error{stage,detail}). It also reveals the routing behavior between structured SEC data and the grounded pipeline. This is exceptional transparency.

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 dense with useful information. It front-loads trigger phrases and a high-level purpose, then provides routing details, verdict enum, citation info, and critical failure semantics. Every sentence adds value, but it could be tightened; the enumeration of verdict types and examples slightly lengthens it without losing necessity.

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 no output schema, the description fully specifies expected return values (verdict types, actual value with citation, reasoning) and handles failure modes (could_not_verify, unsupported) with actionable guidance. For a complex tool with two parameters, it explains routing, error semantics, and usage constraints, making it complete for an agent to decide and invoke.

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 baseline is 3. The description adds meaningful context beyond the schema: it explains that the claim is natural-language e.g. sentences, and that tolerance_pct overrides the implied tolerance, with a default capped at 5 and a purpose for hallucination detection (1–2%). This adds practical guidance on how to set the parameter.

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 query patterns and a clear verb ('validate claim') and resource ('against authoritative sources'). It explicitly scopes to factual claim verification and distinguishes itself from sibling tools by describing its consolidated pipeline that replaces 4–6 sequential calls, making it clearly a claim-checking tool rather than a search or research tool.

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 a direct usage instruction: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also differentiates between company-financial claims (SEC path) and all other claims (grounded pipeline), providing clear context. However, it does not explicitly name alternative tools to use instead, only implicitly excluding them via its specialized purpose.

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