ask_jevAsk a question about America’s 100 most famous politicians (best president, who would win a fistfight, who has the best hair). Jev, TypeSafe AI’s decision model, scores all 100 and returns its top pick, the runners-up, and how sure it is. Opinion, not fact. Questions about abuse or private traits are refused; accusations only name people at 90% or higher.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | The question, in plain words. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint/openWorldHint annotations, the description discloses the internal mechanism (scores all 100), the response shape (top pick, runners-up, certainty), the epistemic status ("Opinion, not fact"), and two refusal rules. That is unusually rich behavioral context for a query tool.
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?
Three tight sentences: purpose first, output contract second, constraints last. Every clause carries information, and nothing is repeated from the schema.
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?
There is no output schema, so the description carries the return-value burden itself and does so — naming the top pick, runners-up, and confidence. Combined with the refusal rules, an agent has everything needed to decide to call it and how to phrase the question.
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 100%, so the baseline is 3, but the description earns extra credit by illustrating what a well-formed question looks like and by implying the content limits (opinion-style, about the 100-politician set) that the schema's minLength/maxLength cannot express.
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 ("Ask a question about America's 100 most famous politicians") and even sketches the answer shape (top pick, runners-up, confidence). It never names the sibling list_politicians, so an agent must infer the ask-vs-enumerate split rather than being told it.
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?
Concrete example question types ("best president, who would win a fistfight, who has the best hair") show the intended register, and the refusal policy for abuse/private traits plus the 90% threshold for accusations set clear boundaries. What's missing is explicit routing against list_politicians or guidance on what to do when the question falls outside the 100-politician set.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.