Skip to main content
Glama

doubao_generate_image

Generates an image from a text prompt through Doubao’s web interface, supporting reference images, Seedream model choice, custom aspect ratios, local saving, and diagnostics.

Instructions

通过豆包网页生成一张图片,支持参考图、Seedream模型和自动/任意文本比例。一次提交,不自动重发;返回本地图片、实际宽高、网页模型证据、对话链接和诊断。

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": {
      "prompt": "<prompt>"
    },
    "name": "doubao_generate_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoseedream5.5
promptYes图片提示词
allow_proNo明确选用会员模型时设为true
output_dirNo可选本机绝对输出目录
aspect_ratioNoauto 或任意正数比例,例如9:16、21:9、2.35:1。实际支持程度由豆包决定。auto
timeout_secondsNo
reference_imagesNo本机参考图绝对路径,支持PNG/JPEG/WebP/APNG

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does disclose key behavior: a single submission with no automatic resend ('一次提交,不自动重发'), plus the return payload (local image file, actual width/height, webpage model evidence, conversation link, diagnostics). It stops short of stating authentication requirements, failure/timeout behavior, or concurrency limits for a browser-driven tool.

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?

Two dense sentences: the first front-loads purpose and capabilities, the second covers the one-shot submission semantics and the return payload. No filler, though the second sentence packs five return items into one clause, which is information-dense but slightly harder to scan.

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 7-parameter tool with no annotations and no output schema, the description does substantial work: it explains the non-retry contract and enumerates returned values, which would otherwise be invisible. Remaining gaps are auth/login state and what diagnostics or failures look like, which matter for a browser-automation tool.

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?

Schema description coverage is 71%, so the schema already documents prompt, output_dir, aspect_ratio, reference_images and allow_pro. The description reinforces the reference-image, model, and aspect-ratio capabilities and echoes the caveat that actual ratio support is decided by Doubao, but adds no meaning for timeout_seconds or output_dir beyond the schema. Baseline 3 applies.

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

Purpose4/5

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

The description gives a specific verb and resource ('通过豆包网页生成一张图片') plus a capability scope (reference images, Seedream models, auto/arbitrary aspect ratios). It is unambiguous versus the only sibling doubao_status, though that differentiation comes from the name gap rather than explicit wording.

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

Usage Guidelines3/5

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

Usage is only implied by the capability list — an agent can infer it is for image generation with optional reference images or a chosen Seedream model. There is no explicit when-to-use / when-not-to-use statement, no mention of the sibling doubao_status, and no stated prerequisites such as needing a logged-in Doubao web session.

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

Deploy Server

Other Tools