Skip to main content
Glama
Threads MCP

Threads MCP

by kerwilgil

Publish Threads image

threads_publish_image
Idempotent

Publishes one approved image post (text plus public HTTPS image_url, optional topic_tag) to Threads; uses a stable idempotency_key and waits for media FINISHED to prevent duplicate retries.

Instructions

Publish one approved image post (text + public HTTPS image_url, optional topic_tag of 1-50 characters without '.' or '&') to Threads. idempotency_key must remain stable for retries of the same logical publication. The media container is published only after Threads reports it FINISHED. The tool prevents blind retries when provider outcome is unknown.

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": {
      "text": "<text>",
      "image_url": "<image_url>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "threads_publish_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
image_urlYes
topic_tagNo
idempotency_keyYes

Output Schema

NameRequiredDescriptionDefault
statusYes
messageNo
post_idNo
permalinkNo
recoveredNo
idempotency_keyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Adds real behavior beyond the annotations: the media container is only published after Threads reports FINISHED, and the tool avoids blind retries when the provider outcome is unknown. Annotations already cover idempotency and open-world/safety hints, and the description usefully confirms and elaborates them; auth or rate-limit behavior is still unstated.

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?

Front-loaded with the action and the required media constraint, then the idempotency and async-publish caveats. Four dense sentences with no filler or repetition.

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 an open-world write tool with an output schema and four parameters, the description covers the core risk areas: idempotent retry semantics and the FINISHED-container precondition. Missing only secondary context such as permission/authorization expectations or the meaning of the returned result beyond the output schema.

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

Parameters4/5

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

Schema coverage is 0%, so the description must carry parameter meaning, and it largely does: image_url must be public HTTPS, topic_tag is 1-50 characters and cannot contain '.' or '&', and idempotency_key must remain stable across retries. The text parameter gets no guidance (length, links, mentions), leaving one gap.

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 resource ("Publish one approved image post ... to Threads") and pins the required inputs (text + public HTTPS image_url), which clearly separates it from threads_publish_text and the read-side siblings.

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?

Gives clear conditions for use: one approved image post, and idempotency_key kept stable on retries of the same logical publication. It stops short of explicitly naming when to prefer a sibling (e.g., text-only publishing) or listing exclusions, so it lands at 4 rather than 5.

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