Skip to main content
Glama

send_image

Sends an image to a QQ friend or group from a URL, local path, file URL, or base64, with an optional caption or sticker mode.

Instructions

Send a picture (http(s) URL, local path on the server, file://, or base64) to a friend or group, optionally with a caption. Set as_sticker to send it as a 表情 sticker.

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": {
      "target": "<target>",
      "image": "<image>"
    },
    "name": "send_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
imageYesURL / path / base64 of the image
targetYesWho to talk to: "qq:<QQ号>" for a friend/private chat, "group:<群号>" for a group, a bare number, or a friend remark/nickname/group name (must be unambiguous).
captionNoText sent with the image
as_stickerNoSend as sticker (subType 1)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, open-world, non-destructive write, so the safety profile is partly covered. The description adds real context by disclosing the four accepted image source forms (including that a remote URL will be fetched and a local path read server-side), but says nothing about permission requirements, size/format limits, or what happens when a URL is unreachable.

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

Conciseness5/5

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

Two tight sentences with the core action and accepted input forms front-loaded, followed by the optional caption and sticker flag. No filler or redundancy.

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

Completeness3/5

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

For a 4-parameter write tool with annotations but no output schema, the description should indicate what a successful call yields (e.g., a message id or status) and flag common failure modes. Those are absent, though the input side is adequately covered.

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 100%, so all four parameters are already documented, including target formats and the as_sticker flag. The description adds only marginal nuance: that the caption is optional and that as_sticker renders the image as a 表情 sticker, which goes slightly beyond the schema's 'subType 1' note.

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 uses a specific verb plus resource ('Send a picture ... to a friend or group') and enumerates the accepted image sources (http(s) URL, local server path, file://, base64), which lets an agent distinguish it from text-sending siblings like send_text or send_msg. It stops short of explicitly naming the near-neighbors it must be distinguished from, such as can_send_image or the various send_* media tools.

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 resource: use it when the payload is an image rather than text or a file. There is no explicit when-not guidance and no mention of prerequisites such as checking can_send_image first, nor of what to do when the target cannot be resolved.

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