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

Beyond the annotations (readOnlyHint, openWorldHint, etc.), the description discloses crucial behavioral details: the verdict types returned, the meaning of 'could_not_verify' (with verification_error{stage,detail}) as an absence of evidence, and the fact that unsupported means no source covers found. It also reveals a performance benefit ('Replaces 4–6 sequential calls'). This is substantial behavioral context that annotations alone do not provide.

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 moderately long but well-structured: it opens with actionable example phrasings, states the core purpose, explains the two processing paths, and wraps up with an important caller warning. Each section earns its place, though the list of example queries could be slightly trimmed. It is not overly verbose for the tool's complexity.

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 no output schema, the description fully accounts for return values (verdict, value with citation, reasoning) and error handling ('could_not_verify' vs 'unsupported'). It also covers the tool's scope, routing logic, and performance characteristics, making it self-contained for an agent to decide and invoke correctly. Complexity is high and the description meets that bar.

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 description coverage is 100%, so the baseline is 3. The description does not add parameter-specific semantics beyond the schema; it merely mentions 'exact percent-delta math' and gives examples of the claim parameter. Since the schema already fully describes both parameters (claim and tolerance_pct), the description provides marginal added value for this dimension.

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 explicitly names the tool's purpose: 'natural-language claim verification against authoritative sources' and provides multiple example query forms ('fact check', 'verify the claim that...'). It further differentiates between two internal processing paths (SEC EDGAR for company-financial claims vs. grounded pipeline for any other factual claim), making the tool's scope precise and distinct from sibling 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?

The description states clearly 'Use whenever the agent needs to check whether something a user said is factually correct.' It also explains the automatic routing for company-financial vs. other claims, which clarifies when the tool is appropriate. However, it does not explicitly mention alternatives or when not to use this tool, so it lacks explicit exclusion/exclusion guidance.

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