get_image_batch

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety bar is low. The description still adds value by disclosing that reads are local/free, hit no provider, and return 'last observed' (i.e. possibly stale) state rather than live data.

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 front-loaded sentence with semicolon-separated clauses; the scoping statement ('本地') and the negative boundaries are ordered sensibly. No filler, though the three negated verbs could be tightened.

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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The description supplies enough to call it correctly; only an explicit sibling reference is absent.

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 both required params (thread_id, checkpointer) carry their own pattern and length docs. The description adds no parameter-level detail, so this is the baseline 3 where the schema does all the work.

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 ('免费读取本地持久化检查点') and enumerates what is restored (task_id/provider_task_id/最后观察状态). The negations ('不查询供应商、不提交、不等待成图') implicitly separate it from wait_image_task and submit_image_batch, but no sibling is named explicitly, so differentiation is inferred rather than direct.

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 clear context ('免费…本地持久化' implies the cheap cached path) plus explicit when-not boundaries: it does not query the provider, submit, or wait. What's missing is an explicit positive alternative (e.g. 'for live status use get_batch_image_task'), so the agent must infer the switch condition.

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