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

Annotations already declare readOnly, idempotent, non-destructive, and open-world. The description adds genuinely new behavioral context: ranking precedence and the explicit disclaimer of 'no clinical interpretation', which bounds what the agent should infer from the result. It stops short of describing result shape or item-level constraints, so not a 5.

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?

Two densely packed sentences with no filler; the read-only privacy constraint is front-loaded, then the ordering rule, then the bounded return value. Every clause carries information.

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?

An output schema exists, so return-value detail is unnecessary, and the description correctly bounds the result ('one next action', 'no clinical interpretation'). The main remaining gap is guidance on when this tool is preferred over the many adjacent work/status tools.

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% for the single 'items' parameter, whose schema description ('Private CareWork items already known to the caller') already carries the semantics. The description reinforces the caller-supplied/private framing but adds no element-level or shape guidance beyond that, so the baseline 3 applies.

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 specific operation (prioritization over caller-supplied CareWork) with a clear read-only caveat and a defined output ('returns one next action'). An agent can distinguish this ranking tool from siblings like find_work or work_status, which locate work rather than order 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?

The priority rules ('qualified-human routes outrank routine work; blocked work outranks creating more work') tell the agent how ordering works but not when to invoke this tool instead of alternatives such as track_followup or find_work. Usage is implied rather than explicit, and no prerequisites or exclusions are stated.

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