Wait Image Tasks

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

With annotations already declaring readOnly/idempotent/closed-world, the description still adds real behavioral detail beyond them: timeout default and bounds, the wait_timed_out/isError signal on expiry, that partial results and completed images are retained and backend work continues, and that client cancellation only aborts this wait. It does not describe the shape of returned results, but an output schema exists to cover that.

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?

Front-loaded with the core purpose and the 'does not submit' exclusion, then proceeds through constraints, timeout behavior, and error semantics. Every clause carries information, though the dense multi-clause punctuation makes it slightly harder to scan than it needs to be.

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 blocking-wait tool this covers purpose, limits, timeout behavior, failure signaling, and cancellation. The only material gap is the unexplained required thread_id and checkpointer parameters, which an agent cannot infer from anywhere else.

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%, so the description must carry the parameter burden. It documents task_ids (required, non-duplicate, 1–100) and wait_timeout_seconds (default 600, integer 1–1200), but says nothing about the required thread_id and checkpointer parameters, leaving half the schema undocumented.

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 ('等待已有任务…所有指定任务终态后返回结果') and immediately rules out what it is not ('不提交、不重新出图'), which cleanly distinguishes it from submit_image_tasks and generate_images.

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?

Explicitly names the alternative: '查询get_image_tasks不等待' tells the agent to use that sibling for non-blocking polling. It also states the precondition (tasks must already exist) and the error condition for unknown IDs or wrong namespace.

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