Evaluate with Jev

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

Annotations cover readOnly, openWorld, idempotent, and destructive hints, but the description adds critical behavioral context: it sends supplied content to an external API and consumes quota (a side effect not captured by annotations), returns probabilities/confidence/token usage, and notes that question IDs are not seen by the model. No contradiction with annotations.

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 information-dense but every sentence earns its place: purpose, use cases, question mixing, output details, batch guidance, behavioral limitations, and side-effect warning. It is front-loaded with the core purpose and there is no redundant filler.

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 covers everything an agent needs: input semantics, output characteristics, constraints, side effects, and caution for consequential results. It is fully self-sufficient and leaves no major gap.

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?

Even though the schema describes both parameters at 100% coverage, the description adds meaningful semantics: explains the three question types (noul, choice, score), clarifies that IDs are only output keys and that the target item must be identified in instructions, and instructs on batch state usage. This goes well beyond the schema structure.

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 ('Evaluate') and the target resource ('supplied text or JSON with TypeSafe Jev') and enumerates concrete use cases (classify, triage, score, judge, compare, audit). It also clearly differentiates by listing what it does not do (fetch URLs, browse, generate explanations, modify data), so an agent can distinguish it from other tools even without siblings.

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?

Provides explicit when-to-use guidance (evaluate text/JSON) and explicit exclusions (does not fetch URLs, browse, generate explanations, or modify data). It gives batch-specific instructions (include all items in state, identify target item in question instructions) and a safety instruction (review uncertain or consequential results). This is far beyond a bare 'use for evaluation' statement.

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