veritas_type_gate

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

Despite no annotations, description discloses return format (JSON with verdict and reason_code) and enumerates all possible reason codes. No side effects or authorization details are given, but the primary behavioral trait (validation with structured output) is well-covered.

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?

Two compact sentences: first defines purpose and checks, second gives usage timing and return format. No wasted words, front-loaded with key information.

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 input structure, output format, and pipeline placement. Lacks explicit mention of prerequisite gates (e.g., intake), but the phrase 'after intake' implies it. Output schema is absent but description compensates with reason codes.

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?

Input schema has 100% coverage with rich descriptions, but the description adds value by noting that all claim fields are optional for partial evaluation and by listing the specific type checks performed, which is not in the schema.

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?

Description clearly states the tool enforces type-level correctness with specific checks (unique primitives, non-empty domains, operator arity, etc.) and positions it as Gate 2/10 in a pipeline, distinguishing it from sibling gates like intake or evidence.

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 says 'Use this after intake to catch structural errors before evidence evaluation', providing clear sequencing context among sibling pipeline tools. Does not list exclusions but the context is sufficient.

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