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

With no annotations, the description carries the full burden, and it does disclose two genuinely useful behaviors: the retry restarts 'from now' rather than resuming, and attempt history is preserved while the attempt count resets. It omits error behavior for non-failed tasks, idempotency, and what the call returns, which for a mutation tool with zero annotation coverage is a real gap.

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 short sentences, front-loaded with the action and followed by the key state caveat. Every clause carries information; there is no filler.

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 single-parameter tool with no output schema, the description covers the essential semantics: restart point and attempt-history retention. Only the failure precondition and response behavior are unaddressed, which are minor omissions at this complexity.

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% and the task_id description already explains the format and where the id comes from (schedule_http or queue_http). The description adds no additional meaning about the parameter, so 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 verb and resource ('Retry a failed task'), which is clearly distinct from siblings like cancel_task and get_task. It stops short of naming any sibling explicitly, so the differentiation is implicit rather than spelled out.

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 'a failed task' implies a precondition, so an agent can infer this is for tasks in a failed state. But there is no explicit statement of when to use this versus cancel_task or get_task, nor what happens if the task is not failed.

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