Nack (fail/retry) a task

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

The description discloses key behaviors: default re-queue until maxAttempts, then dead; delayMs for backoff; requeue:false for immediate failure; and the need for a fencing token. Since there are no annotations, these details are essential and are provided. It does not mention authentication or return values, but the core behavior is transparent.

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 sentences, front-loaded with the purpose. Each sentence adds necessary information: the action, the default behavior, and the key parameter effects. No redundant content.

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?

The tool involves claim tokens and retry semantics, and the description covers the main behavior. However, without an output schema, it does not explain what the tool returns or what error conditions might occur (e.g., invalid fencing token). The dead queue concept is mentioned but not elaborated, leaving some gaps for a complex task queue operation.

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?

The input schema describes 3 of 5 parameters (error, delayMs, requeue). The description adds meaning for fencingToken by stating it must carry the claim, and clarifies delayMs and requeue semantics, though it does not describe taskId or error explicitly. Overall, it partially compensates for the undocumented schema parameters.

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 opens with 'Report a claimed task as failed,' which is a specific verb+resource statement. It clarifies the retry/fail behavior and the requirement of a fencing token, distinguishing it from sibling tools like ack_task and enqueue_task. The title 'Nack (fail/retry)' also aligns.

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?

It gives clear context for when to use this tool: to fail a claimed task, with a fencing token. It explains the default re-queue behavior and the requeue:false option, but does not explicitly contrast with ack_task or other sibling tools. No exclusions are stated, but the context is clear.

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