Jev pre-analysis (advisory)

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

Adds substantial context beyond the annotations: the payload leaves the boundary to a third party at TypeSafe, has a hard 12 KB cap, can be refused for missing consent/key, and is never retried automatically — an important non-obvious trait given idempotentHint=false. It also discloses the return shape (answers plus flagged items) and that results are advisory, not a verdict.

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 tight sentences, each carrying distinct information — payload, destination, questions asked, return shape, advisory status, preconditions, retry policy. The core purpose is front-loaded with 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 one-parameter external-call tool with no output schema, the description covers who receives the data, what is asked, what comes back, refusal conditions, and the epistemic weight of the result. Nothing an agent needs to invoke it safely is missing.

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 does: the single 'task' parameter is characterized as a task description with a 12 KB ceiling matching the schema maxLength. It does not describe expected internal structure or formatting conventions for the payload, so it falls just short of full compensation.

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 concrete verb and resource: send a task description to a named external service (Jev at TypeSafe) for pre-analysis against fixed questions. The 'pre' framing plus 'Advisory' makes it distinguishable from agiw_jev_post, though it never names that sibling explicitly to route the agent.

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 clear preconditions ('Refused unless consent is recorded and a key is available') and sets expectations ('Advisory, not a verdict'), which tells the agent this is not a gate. It does not explicitly say when to choose this over agiw_jev_post or agiw_readiness.

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