Export Validated Reference Replica

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint=false, so the safety profile is covered; the description adds real context beyond that: it does not approve and does not charge, both current and historical revisions are queryable, size and batch limits, and that the same compiler as real submission is used. It stops short of describing failure modes for a non-confirmed or over-limit revision.

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?

Four dense sentences with the read-only/no-charge constraint front-loaded, followed by limits and then formatting conventions. Every sentence carries information, though the compiler/anti-bypass sentence is long and could be split for readability.

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 not be explained, and annotations cover the safety profile; the description fills the remaining gaps an agent needs (validated-only, limits, batch size, prompt and image ordering conventions, bypass warning). The one meaningful hole is the semantics of the revision parameter.

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 carries the full burden for design_id and revision. It only gestures at revision semantics with '当前/历史版本可查' (current/historical versions queryable) without ever mapping that to the nullable integer parameter or stating what null/default means, and says nothing about the design_id pattern or format.

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 (只读导出/read-only export) plus the resource (新版共享复刻的已校验完整Markdown) and enumerates exactly what is returned: Markdown, unified style summary, task configuration, and ordered image roles. It implicitly separates itself from export_reference_replica via the '已校验' qualifier, but never names that sibling, so differentiation is left partly to inference.

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 concrete usage conditions: only the current confirmed version can be submitted, up to 71 items per full set, execution in batches of max 20. The closing warning ('do not feed task back into the generic image generation entry to bypass version confirmation or charging') is an explicit when-not rule. It lacks a direct pointer to which sibling to use for the unvalidated/raw export case.

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