trust_verdict

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

With no annotations, the description fully carries the behavioral burden. It explicitly discloses that the engine NEVER invents a score, specifies the two special statuses ('insufficient-data' with null score, 'evidence-disputed'), instructs agents to report those statuses as-is, and mandates that inputs must be real, citable evidence. This level of disclosure exceeds expectations.

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, each earning its place: purpose, input structure, and behavioral caveats. The description is front-loaded with the primary action and includes a concrete input template. Minor density in the middle sentence could be tightened, but there is no fluff.

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 (nested input, no output schema), the description covers input structure and special statuses well. It stops short of describing the full successful response shape (e.g., the score value and evidence binding), but the mention of statuses and the 'report as-is' directive gives agents enough to handle the key edge cases. A short note on the normal payload would make it complete.

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 input schema only says 'Engine input document per trust/spec.md section 3,' which is nearly meaningless without external specs. The description compensates by spelling out the exact expected object shape: {engine_version, subject:{agent_id,...}, context, observed_at, signals:{erc8004:[], needle_drop:[], first_spin:[]}}. This adds critical structural semantics beyond 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?

The description opens with a specific verb and resource: 'Score agent trust with the CWI Verdict Engine v1.0.0.' It also adds distinguishing traits ('deterministic, evidence-bound') that separate it from ledger or verification siblings. An agent can immediately identify this as the trust-scoring tool.

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 for when to use the tool (to score agent trust) and how to structure the input, but it never explicitly names alternatives or conditions for not using it. It does not reference sibling tools or state exclusions, leaving the when-not-to-use guidance to inference.

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