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

Annotations already declare the tool read-only and safe. The description adds value by disclosing the LLM back-end and the fallback behavior for opinions or live-data claims ('Returns 'uncertain''). This exceeds what structured annotations convey, though it doesn't detail latency or reliability bounds.

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 tight and front-loaded: the core function and output are in the first sentence, followed by succinct use-case examples and an edge-case note. No filler or repetition.

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?

The tool is simple (one parameter, no output schema, read-only annotations). The description covers the return structure (verdict, confidence, reasoning) and a key edge case. It doesn't explicitly state the response format (e.g., JSON structure), but that's minor given the description already specifies the components.

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?

The schema fully describes the single 'claim' parameter (100% coverage), so the baseline is 3. The description adds a bit of context ('any factual claim') but does not elaborate on input format, constraints, or examples beyond what the schema already provides.

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 states a specific verb ('fact-check'), a resource ('any factual claim'), and the precise output shape (verdict, confidence score, reasoning). It clearly distinguishes itself from the crypto-focused sibling tools by its generic, LLM-based fact-checking scope.

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 explicit use cases ('content moderation, chatbot/agent guardrails, and misinformation screening'), providing clear context for when an agent should invoke it. It doesn't name alternatives or exclusions, but the tool's generic nature and the obvious contrast with crypto siblings make its intended role evident.

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