Zhenzhen Image MCP

run_image_batch

Idempotent

Executes up to 20 paid image generation or edit tasks synchronously with bounded concurrency, stable task IDs for deduplication, and SHA-256 replay checks to prevent duplicate charges.

Instructions

同步执行1–20项收费生成/编辑，默认并发5，完成并校验落盘后返回。稳定三元组防重；重放验证文件SHA-256，不重复收费；超时/未知结果禁止重发。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "checkpointer": "<checkpointer>",
      "thread_id": "<thread_id>",
      "tasks": "<tasks>"
    },
    "name": "run_image_batch"
  }
}

Input Schema

Name	Required	Description
`tasks`	Yes
`thread_id`	Yes	稳定的本地检查点命名空间/会话键，1–128字符。
`checkpointer`	Yes	稳定的本地检查点命名空间/会话键，1–128字符。
`max_concurrency`	No

Output Schema

Name	Required	Description	Default
`note`	Yes
`tasks`	Yes
`status`	Yes
`next_tool`	Yes
`thread_id`	Yes
`checkpointer`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.4.0Oct 23, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already flag non-read-only, open-world and idempotent, and the description adds real operational context: charges money per image, default concurrency, post-write verification, dedupe via a stable identity triple, SHA-256 replay verification preventing double billing. It also states a hard failure-mode rule about resending on timeout, which no annotation conveys.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, scale, and default concurrency, then the dedupe and retry-safety rules as follow-up clauses. Dense but every clause carries information; only the vague '稳定三元组' phrase blurs rather than earns.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid, checkpointed batch mutation with an output schema already present, the description covers sync semantics, concurrency, dedupe, and the no-resend failure rule. Remaining gaps are partial-failure reporting and the meaning of the identity triple, which the schema only partially covers.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description clarifies the tasks bound (1–20) and the default concurrency of 5, matching the schema limits. However, with 50% schema description coverage, thread_id/checkpointer get no treatment in the description, and the '稳定三元组' (stable triple) that prevents duplicate charges is left ambiguous about which three keys form it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and scope: synchronous execution of 1–20 paid generation/edit tasks, default concurrency 5, returning after files are written and verified. The word 同步 implicitly and effectively separates it from the submit_image_batch sibling, so an agent can route between them without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 1–20 batch framing plus the explicit prohibition '超时/未知结果禁止重发' (do not resend on timeout/unknown result) give concrete use and misuse rules. It never names a sibling alternative (submit_image_batch, generate_image) directly, so the routing is inferred rather than stated.

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

Deploy Server