Score input

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

Discloses external service usage (Jev AI), API key requirement, credit consumption, rate limits, and no retries. It also notes the output location (answers.result). This goes well beyond the sparse annotations (readOnlyHint false, etc.) and gives the agent important operational context.

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?

Four sentences, no redundant words. Core purpose is first, then alternative, then requirements and side effects. Every sentence adds new information; no 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 3 required params and no output schema, the description provides enough: what it returns (score, legend, probabilities, model, usage), prerequisites (API key), and side effects (credits, rate limits, no retries). An agent can safely invoke it without further documentation.

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 covers all parameters at 100%, so baseline is 3. The description adds meaningful details: levels are ordered and zero-based, score is fractional, and state is sent to Jev AI. These clarify how the parameters relate to the tool's behavior beyond the schema.

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 clearly states the tool rates input on an ordered 2–20 level scale, which is specific and distinguishes it from the yes/no tool (jev_check). It also gives the return format, so an agent knows exactly what to expect.

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 explicitly directs to use jev_check for yes/no, providing one clear alternative. It does not compare against jev_classify, jev_gate, jev_decide, jev_saved_judge, but the purpose (rating on a scale) implicitly differentiates it. Overall it gives clear context but not exhaustive exclusions.

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