Release a pre-approved task you cannot finish, providing a reason so it returns to Next Up for reassignment.
Give back a pre-approved task you took and cannot finish, with why. It goes to Next Up for somebody else, and your reason is posted on it.
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | ||
| why | Yes | What stopped you, for whoever takes it next. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the disclosure burden and delivers real behavioral value: the task moves to Next Up (queue state change) and the reason is posted on the task (a visible side effect). It omits whether ownership is required, whether it errors if the task isn't yours, and whether the release is reversible.
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 tight sentences, front-loaded with the action and its outcome; no filler or redundancy. 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?
For a simple two-parameter task tool with no output schema and no annotations, the description covers what it does and its side effects adequately. It could mention preconditions (task ownership) and failure behavior, but nothing essential is missing for correct invocation.
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 50% — only 'why' is documented, and the description adds to it by explaining the reason is posted publicly for the next taker. The 'ref' parameter is never explained in either the schema or the description, though 'a task you took' weakly implies what it identifies. Baseline 3 for partial coverage 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?
States a specific verb (give back/release) and a specific resource (a pre-approved task you took), and clarifies the outcome — the task returns to 'Next Up' for another person. It effectively contrasts with the sibling fenbs_next_approved_task (taking a task) by implying this is the reverse action, though it never names the sibling explicitly.
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 a clear triggering condition: use it when you took a pre-approved task and cannot finish it. There are no explicit exclusions or named alternatives, but the 'cannot finish' framing is a fairly precise when-to-use signal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.