Classify input

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

Beyond the annotations (which only signal non-read-only, open world, non-idempotent, non-destructive), the description discloses external data sent to Jev AI, account credit consumption, rate limits, and no automatic retries. This is exactly the behavioral context an agent needs and does not contradict any annotation.

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 short, front-loaded with the core behavior, and every sentence adds necessary information: purpose, output, alternative, authentication, side effects, and retry behavior. No filler or redundant material.

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 an externally calling tool with no output schema, the description covers purpose, return shape, authentication, cost, rate limits, and retry behavior. An agent has enough information to select and invoke the tool 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 100%, so the parameters are already documented. The description adds some context by saying input is sent to Jev AI, but it does not add detailed parameter semantics beyond the schema; baseline 3 is appropriate.

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 and resource: 'Choose one labelled option for routing, categorization or intent detection', which is much more informative than the title. It also clarifies the output (choice, confidence, probabilities) and distinguishes from jev_score for ordered levels.

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 gives explicit routing guidance: use jev_score when ordered levels are needed, implying this tool is for categorical choices. It also provides operational prerequisites and constraints: requires JEV_AI_API_KEY, consumes credits, rate limits, and no automatic retries.

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