kev_evaluate

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

There are no annotations, so the description carries the full behavioral disclosure burden. It explains the three question modes with their return shapes, explicitly warns that confidence is a separate signal from the top probability, and describes the high-level return fields (upstream model, answers, usage, latency_ms). This goes well beyond a minimal description.

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?

Though longer than average, the description is dense and well-structured with bullets and code-formatted types. The main purpose is front-loaded, followed by parameter semantics, a key caveat, and return information. Every sentence adds necessary value, and the length is justified by the tool's 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 sparse schema and lack of annotations, the description is remarkably complete. It covers all valid question types, the meaning of each output field, the confidence caveat, and the overall response structure. The output schema exists, but the description adds essential interpretation details and usage nuances, leaving no major invocation gaps.

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 has 0% description coverage, and the description fully compensates. It defines 'state' as any JSON value and documents the 'questions' object with concrete formats for choice, score, and noul questions, including output fields. An agent can construct a valid call without needing additional parameter documentation.

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 ('Evaluate') and a clear resource ('a decision state using Kev's pointer-head model'). It also states that several questions may be packed into one call and enumerates the three question types, so an agent can immediately distinguish this from sibling tools like kev_list_models or kev_permute.

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: use this tool when you need to evaluate a decision state with Kev's pointer-head model, and it even advises that multiple questions can be packed into a single call. However, it does not explicitly mention sibling alternatives or state when not to use this tool, so it lacks full exclusionary guidance.

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