image_batch_edit

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

With no annotations provided, the description carries the full burden and delivers rich behavioral detail: concurrency strategy (5 for gpt-image-2, serial+1.5s gap for the openai line), failure isolation ('任意一张失败不影响其他张'), high-resolution auto-switching to serial processing, rate-limit risk disclosure, and note that cost/time scale linearly with batch size. This exceeds what any annotation set would typically provide.

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?

Well-structured with clear section headers ([WHAT], [WHEN TO USE], [并发策略], [LIMITS], Args, Returns, Examples) and front-loaded summary. Though long, every block earns its place — this is a complex 6-parameter batch tool with output-format documentation and routing logic; the length is proportionate to the complexity. No filler or redundant restatement.

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?

Given the tool's complexity, 0% schema coverage, and an output schema, the description covers everything an agent needs: input parameter semantics, return format (ok/total/succeeded/failed/concurrency/results), concurrency and failure behavior, limits, and a working example. The presence of an output schema relaxes the burden on return-value explanation, and the description still documents it. Complete.

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 compensate, and it does so thoroughly. The Args section gives each parameter real meaning beyond the schema titles: prompt gets an example, size gets the 1K/2K/4K values and default, model gets the two accepted values, save_dir gets the filename pattern batch_<ts>_<idx>.png and the security-root constraint, api_key gets its MICU_API_KEY override behavior with base_url locking noted. Full compensation for the coverage gap.

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 opening line states a precise verb+resource+scope: 'N 张输入图 → N 张输出图，每张独立应用同一指令' (batch edit N images, each independently applying the same instruction). The [WHAT] section plainly states it calls image_edit per image and merges results. It differentiates itself from siblings by explicitly declaring '用多张图作风格参考画 1 张新图' is NOT this tool, and routes single images to image_edit. Unambiguous.

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 [WHEN TO USE] section gives explicit selection criteria: use this tool when the user has multiple images all needing the same modification (watermark, background, color grading), use image_edit for a single image, and explicitly states the multi-reference case is not implemented. It also adds concurrency strategy per model line. Nothing is left to inference.

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