Export Reference Replica

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

Annotations already cover read-only and idempotency, but the description adds real value beyond them: no cost, no submission/approval side effect, that exported content is preserved under the same compiler used for actual submission, and that input_images must be attached in role order. It stops short of describing what invalid ids or an over-limit panel set do, which keeps it off a 5.

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?

The purpose is front-loaded, but the paragraph mixes Chinese and English and drifts into tangential detail about resolution tiers, api_format/endpoint display, and shared compilers. Some of that is useful context; the api_format/endpoint sentence in particular does not obviously earn its place in a caller-facing definition.

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 an output schema present, return values needn't be spelled out, and the annotations plus the described follow-up workflow cover the safety profile adequately. The remaining gaps are the undocumented design_id/revision semantics and the absence of any differentiation from export_validated_reference_replica.

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 does explain the 1–20 panel range (matching panel_ids minItems/maxItems), but it never explains design_id, revision, or the meaning/validity of panel_ids values, and it spends words on fields like prompt_target, execution_model, and api_format that aren't parameters at all.

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 states a specific verb and resource: a free export of 1–20 fully executable Markdown items plus image ordering, explicitly noting it neither submits nor approves. That distinguishes it from the submit_* siblings, but it never mentions the near-identical sibling export_validated_reference_replica, so an agent can't tell those two apart from the text alone.

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 frames the intent ('用于研讨并适配本服务三个模型；不提交、不批准') and names a post-export workflow: inspect_design_images to view results and review_reference_replica to record evidence. However, it gives no guidance on when to choose this export versus export_validated_reference_replica or build_reference_replica_prompts, leaving the main sibling choice to inference.

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