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

With no annotations to rely on, the description fully discloses behavioral traits: verdict values (consistent/contradicts/unverifiable), non-persistence, rate limits with exact thresholds and error format, fail-safe deny behavior, and the distinction between public demo data and user data. This is comprehensive beyond a basic 'check' operation.

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 dense and relatively long, but it is front-loaded with the core purpose and structured into two paragraphs. Each sentence adds meaningful details (verdict domain, rate limits, fail-safe), yet it could be trimmed without losing essential info; still, the length is justified by 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?

Given the tool's complexity and the presence of an output schema, the description covers most contextual aspects: return receipt fields, verdict semantics, rate-limit error behavior, scope, and non-persistence. The only notable omission is the `focus` parameter's purpose, which prevents a perfect score.

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 0%, and the description effectively explains the main `claim` parameter (natural language claim, SPO extraction) but provides no information about the `focus` parameter. Since only two parameters exist, leaving one undocumented is a clear gap, but the claim parameter is well-contextualized.

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 core function: extract SPO triples from a natural language claim and check them against a grounded fact store. It distinguishes from siblings by emphasizing the NL-gate/claim-based approach and by outlining a specific, auditable receipt structure.

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 clear context on when to use the tool: it is advisory, never persists, and is meant for consistency checking rather than writes (check ≠ save). It does not explicitly compare to sibling tools like check_triple or list_facts, but mentions that add_fact is absent in PUBLIC_DEMO-mode, implying it is not for writing.

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