queue_retry

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the one meaningful side effect (state moves to pending), but omits whether this counts against a retry limit, whether it errors for non-failed tasks, whether it is idempotent, whether a separate queue_run is needed to actually execute, and what permissions are required.

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 short sentence with the state transition front-loaded and no filler. It is appropriately sized for the tool, though its brevity reflects under-specification rather than disciplined editing.

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?

With no annotations, no output schema, and an undocumented required parameter, the description should do more work. It leaves open what the return value is, whether the task re-executes immediately or waits for queue_run, and whether retries are bounded.

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 0% for the single required `id` parameter, and the description never mentions it. The agent can only infer that `id` is the identifier of the failed task. This is the one gap the description was best positioned to close and it does not.

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 and resource with the resulting state transition: reset a failed task to pending. That distinguishes it cleanly from the queue_* siblings (add/run/list/remove) without needing to name them. It stops short of a 5 only because the object of the action ('task') is never tied to the lone `id` parameter.

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 phrase 'failed task' implicitly scopes usage to tasks in a failed state, which is useful context. However, it never states when to prefer this over queue_run or queue_add, nor what happens if the task is not failed. Usage must be inferred from the state transition itself.

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