Fact-check a claim

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

The description discloses key behavioral aspects: it uses an LLM, returns a verdict with confidence and reasoning, and handles edge cases (opinions, need for real-time data). Without annotations, the description adequately informs the agent of the tool's behavior and limitations.

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 extremely concise—two sentences that efficiently convey purpose, output, and usage boundaries. Every sentence adds unique value without redundancy.

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 description fully covers the tool's functionality: input (a claim), output (verdict, confidence, reasoning), and special cases (returns 'uncertain' for non-factual or real-time claims). No output schema exists, but the description compensates by detailing the return structure. For a simple tool with one parameter, this is complete.

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 single parameter 'claim' is described as 'The factual statement to verify' in both the schema and description. The description adds minimal extra semantic value beyond the schema, so a baseline score of 3 is appropriate given 100% schema coverage.

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 states the tool's purpose: to return a verdict (true/false/uncertain), confidence score, and reasoning for a factual claim. It distinguishes itself from sibling tools (crypto_regime, crypto_sentiment, etc.) by focusing on general fact-checking rather than cryptocurrency-specific analysis.

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 lists use cases: content moderation, guardrails, misinformation screening. It also notes when the tool returns 'uncertain' for opinions or claims needing live data. However, it does not mention when to avoid using it or suggest alternative tools.

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