Yes/no question with Jev

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

Annotations only say readOnlyHint/openWorldHint; the description adds substantial context beyond them: the 0..1 probability scale and the trap reading of 0.5, the 4-image / 4 MiB / PNG-JPEG-WebP limits, the JEV_IMAGE_DIRS sandbox for path inputs, the base64 data-URL form, the warning never to put images inside `state`, and model capability rejection behavior.

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?

Front-loaded with purpose and return semantics before parameter detail, and nearly every sentence carries non-obvious information. It is a dense block rather than a scannable structure, and the image/model constraints bleed into what would otherwise be a clean parameter walkthrough.

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?

An output schema exists, so the return value needn't be re-explained, and annotations cover the safety profile; the description fills the real gaps (image sandboxing, model capability, state/instructions discipline). The only missing piece for correct invocation is guidance on choosing `model` rather than leaving it as a bare 'optional'.

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 coverage is 0%, so the description must carry the load, and it mostly does: `state` (string or JSON object/array), `instructions` (must state the full question, reference structured state via backticked paths like `ticket.messages[0].text`), `criteria` {true,false}, `images` (both shapes with limits), and `provider`. The gap is `model`, which is only called 'optional' with no guidance on valid values or how to discover them (jev.models exists), which matters given the image-capability constraint.

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?

States a specific verb and resource ('Ask TypeSafe Jev one yes/no question about some state') and immediately defines the return semantics as `answer.noul`, a probability 0..1 with 0.5 = equally likely. It also distinguishes itself from the sibling `jev.evaluate` by scoping to a single question, so an agent can pick between them without opening the schema.

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?

Gives an explicit routing rule: 'To ask several questions about the same state, use jev.evaluate instead: it answers them in one request.' It also states when-not conditions for images (only image-capable models, names concrete examples) and notes the server only offers provider 'typesafe', leaving no ambiguity about alternatives.

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