jev_evaluate

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

With no annotations, the description carries the burden. It discloses parallelism, input flexibility, and return contents (calibrated probabilities, confidence scores, token usage), but does not address safety/mutation, auth, or error behavior. Parallel evaluation and return details are useful but not a full behavioral profile.

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 short sentences front-load the router role, the operation, the input types, and the output. Every sentence adds information; no filler or repetition of schema titles.

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?

The description gives a competent overview for selection and basic invocation, but the tool is a multi-question router with nested input and no annotations. It omits how individual typed questions are structured and does not mention credential/model parameters, so an agent is not fully equipped to call it correctly.

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%, so the description must add meaning. It clarifies that 'state' may be unstructured or structured and that 'questions' are typed evaluation questions, but it does not explain 'model' or 'api_key' or the expected shape of a question object.

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 states a specific verb ('evaluates'), a resource ('unstructured or structured state'), and a distinguishing scope ('multiple typed questions (noul, choice, score) in parallel'). This clearly separates it from the single-question sibling tools.

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?

It is identified as the primary proxy router, and 'multiple' plus 'in parallel' signal when to prefer it over the individual typed tools. It does not explicitly state when not to use it or name those tools as alternatives, so it stops short of a 5.

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