evaluate

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals key behaviors: all questions are answered in parallel against the same input, and noul returns a probability 0-1. It does not disclose potential side effects, authentication needs, or rate limits, but for an evaluation tool these are likely irrelevant. The disclosed parallel execution and probability return add meaningful transparency beyond the schema.

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?

The description is two sentences long, with the core purpose front-loaded and no redundant phrases. It efficiently covers the tool's function, the three question types, and a key behavioral trait (parallel execution). Every word earns its place, and the structure is highly readable.

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?

For a tool with nested objects and three question types, the description is largely complete. It explains the primitives and the parallel behavior. The schema already details the criteria structure and the mapping of question ids to answer keys, so the description does not need to repeat those. However, there is no output schema, and the description does not describe the overall response format (beyond noul's probability), which could leave some ambiguity about what the tool returns for choice and score. This slight gap prevents a perfect score.

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 100%, so each parameter is already documented. The description adds value by clarifying behavioral semantics of the question types (e.g., noul returns a probability, choice selects best-fitting option) and the parallel execution model. This goes beyond the schema, which only lists types and criteria, by explaining the expected behavior of each primitive. A baseline 3 is elevated to 4 due to this extra context.

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 clear, specific purpose: evaluating content against typed questions. It names the API (TypeSafe's System One) and model (jev), and lists the three supported question primitives (noul, choice, score). This is far from a tautology and clearly differentiates the tool's function.

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?

While no sibling tools are provided, the description gives strong contextual guidance on when to use this tool: whenever content needs to be evaluated against structured questions. It also explains that the three question primitives can be mixed in a single call, implying flexibility. However, it does not explicitly state when not to use it or mention any alternative approaches, but given the absence of siblings, this is acceptable.

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