veritas_evidence_gate

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

Describes computation of independence, agreement, quality scores, and output format (verdict, reason_code). No annotations provided, so description carries full burden; lacks detail on side effects or prerequisites but is sufficient for a stateless evaluation tool.

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?

Three sentences, front-loaded with purpose, no wasted 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?

Covers purpose, usage, and output; with no output schema, it lists verdict and reason codes. Could mention the claim structure more but schema fills that gap.

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?

Adds context by explaining that the tool checks thresholds and provides output meanings; schema already has 100% coverage with detailed parameter descriptions, so the description complements rather than replaces.

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?

States specific verb ('evaluates evidence sufficiency'), resource ('critical variables'), and distinguishes from sibling tools by naming alternatives for individual calculations.

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?

Explicitly tells when to use this tool ('to verify thresholds') and when to use alternatives ('veritas_compute_quality or veritas_mis_greedy'), providing clear context.

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