Skip to main content
Glama

draft_post

Write a NEW post with AI. If you are about to write post copy, call this instead: it writes from this person's real posts, voice and the client's brand (positioning / audience / pillars). That includes 'write a post about X', 'draft something about Y' and 'turn this into a LinkedIn post': pass the topic, notes or angle as prompt rather than writing the post yourself. Use save_draft only for words the user wrote or pasted. Returns the new draft's post_id and its full text. Nothing is scheduled or published. If the idea is too thin to write from, it saves nothing and asks a question instead; call again with the answer, or with draft_anyway: true. To change the draft afterwards, use revise_draft with that post_id, not draft_post again.

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": "draft_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
imagesNoImages, a video, or one PDF to attach. For ANY image beyond a thumbnail, call upload_image FIRST to get a presigned S3 URL, upload via the returned curl command, then pass the s3_key here. Inline `data` is only for tiny images (≤50 KB); `file_path` is dev-only. A PDF posts as a LinkedIn document (a swipeable carousel): LinkedIn only, one per post, never alongside images or video.
promptYesTopic or instructions for what to write
youtubeNoYouTube-specific options. Required platform inputs: a video must be attached via `images` (the upload tool accepts video MIME types). If `title` is omitted, it is derived from the first line of content (truncated to 100 chars).
platformNoTarget platform. Influences tone and length. Instagram needs an image or video on the post: upload one with `upload_image` (or make one with `generate_image`) and pass its s3_key in `images`.
workspaceNoOptional: the workspace (client) to answer from for this call only, by name (e.g. 'Acme') or numeric id, as returned by list_workspaces. Leave it out to use the current workspace. It does not change the current workspace; use select_workspace for that.
draft_anywayNoSet true to make the writer draft with what it has instead of asking for more context. Use when a previous draft_post call came back with 'Need more to draft this' and the user would rather you just write it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / workspace
      Added value: +{
      +  "description": "Optional: the workspace (client) to answer from for this call only, by name (e.g. 'Acme') or numeric id, as returned by list_workspaces. Leave it out to use the current workspace. It does not change the current workspace; use select_workspace for that.",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare a non-destructive, non-open-world write; the description adds substantial behavior beyond that: nothing is scheduled or published, the return payload is post_id plus full text, and the thin-idea path saves nothing and returns a question instead. That last detail is critical, because it explains an otherwise surprising no-op result and tells the agent how to recover via the answer or draft_anyway.

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?

The decisive instruction is front-loaded in the first sentence, and the dense run-on structure packs when-to-use, alternatives, return value, and the retry loop into one block with little filler. It is slightly redundant in restating 'call this instead' and 'rather than writing the post yourself', which could be one clause.

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

Completeness5/5

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

For a 6-parameter generation tool with nested objects and no output schema, the description still covers what the agent needs: what is produced, what is not (no scheduling or publishing), how to continue after a thin-idea refusal, and which sibling to use for revisions. The only return-value detail needed, post_id and full text, is stated explicitly.

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%, including detailed guidance on s3_key, inline base64 limits, PDF-only title, and the draft_anyway escape hatch, so the schema already carries the parameter burden. The description adds only a modest amount: that topic, notes or angle all belong in `prompt` rather than in agent-authored copy. That is useful framing but not meaning the schema lacks.

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 ('Write a NEW post with AI') and immediately distinguishes it from the two closest siblings by name: save_draft for user-authored text and revise_draft for post-hoc edits. The 'NEW' qualifier plus the AI-generation framing makes the boundary unambiguous without opening any schema.

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

Usage Guidelines5/5

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

Gives explicit when-to-use triggers ('write a post about X', 'draft something about Y', 'turn this into a LinkedIn post') and routes those cases here instead of self-writing. It also states the negative case (save_draft only for words the user wrote or pasted) and the follow-up case (revise_draft with that post_id), so both the entry and exit paths are covered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources