Fact-check a claim against The Nexus

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

With no annotations provided, the description carries the full burden. It discloses the return format (verdict, rationale, confidence, citations) and the caching/rate-limiting behavior. This gives the agent sufficient understanding of the tool's execution characteristics.

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 three sentences, each earning its place: the first defines purpose and output, the second adds constraints, the third states source. No redundant words.

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?

Given the tool's simplicity (one parameter, no output schema), the description covers all essential aspects: what it does, what it returns, and behavioral nuances (caching, rate limits). It is complete for an agent to decide whether and how to invoke it.

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% (one parameter 'claim' is described as 'The claim to check, in plain language'). The description adds no additional meaning beyond the schema, meeting the baseline but not exceeding it.

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 specifies a precise verb ('check'), a concrete resource ('The Nexus's news corpus and public records'), and the unique output (verdict types). It clearly distinguishes from sibling tools like nexus_search or nexus_record_lookup.

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 the tool ('check a factual claim') and hints at constraints (instant for cached, rate-limited for novel). However, it does not explicitly state when not to use it or point to alternatives for non-fact-check queries.

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