jev_rerank

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

With no annotations, the description must carry behavioral disclosure on its own. It does usefully reveal batching granularity (batches of 12), a hard input ceiling (96 items), and a runtime dependency — genuine operational context — but says nothing about ordering of results, determinism, scoring scale, or what happens when the 96-item limit is exceeded.

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?

A single front-loaded sentence with no filler: verb, resource, throughput limit, batching behavior, and runtime prerequisite. Every clause earns its place.

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 and no annotations, so the description should explain the shape of the result (ranked list with scores? ordering? top_k default behavior). It covers input constraints well but leaves the return-value contract entirely to inference.

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 all three parameters are already documented, establishing a baseline of 3. The description adds the 96-item/batch-of-12 constraint relevant to the items array, but adds no new meaning for 'query' or 'top_k' 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?

Clear specific verb (rank) and resource (candidate text items against a query), plus concrete limits (up to 96 items, batches of 12). It does not differentiate itself from the sibling tools (jev_guard, jev_route, jev_verify, jev_arbitrate), but the names are distinct enough that confusion is unlikely.

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?

The description supplies a precondition ('requires JevBridge runtime') which constrains applicability, but gives no explicit when-to-use/when-not guidance or alternative tooling for ranking-like tasks. Usage is only implied by the verb and the prerequisite.

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