verify_claim

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'attach exact spans', hinting at an output behavior, but does not disclose whether the operation is read-only, whether external systems are involved, or what happens when claims are unsupported (e.g., are they ignored or flagged?). This is insufficient for a tool that likely performs an analysis task.

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 a single concise sentence with no filler words. It is front-loaded with the main verb and noun. However, its brevity contributes to under-specification; while structurally clean, it omits crucial detail that would make the content value-dense.

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?

An output schema exists, so return value structure is covered, but the description still lacks operational context. It does not explain what 'supported' means, how claims are identified, whether multiple claims are handled, or the relationship with 'lookup'. Given the tool's potential complexity (verification and span attachment), the description is incomplete for an agent to use it correctly.

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 describes 'text' only by type and length constraints, and schema description coverage is 0%. The description does not mention the parameter at all, leaving the meaning of 'text' completely ambiguous. The description should explain what kind of text is expected (e.g., a document, a sentence, a claim list) and how it is used.

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 clear action ('verify') and a specific target ('claims') with a distinctive outcome ('attach exact spans'). It distinguishes from the sibling 'lookup' by focusing on verification rather than retrieval, though 'claims' and 'supported one' remain somewhat vague.

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?

No guidance is given on when to use this tool versus the sibling 'lookup'. There is no mention of prerequisites, typical input cases, or exclusions. The description implies a verification/annotation use-case but does not explicitly state it.

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