Skip to main content
Glama

revise_draft

Rewrite an existing post from the user's feedback, with AI. Apply the user's feedback to an EXISTING draft and save the revision onto the SAME post. Use this every time the user reacts to a draft you already produced, like 'make it shorter', 'less salesy', 'add a call to action', 'that's not what I meant'. Do NOT call draft_post again to act on feedback: that creates a second, unrelated draft and leaves the first one (with its attached images) behind. Runs the full voice engine server-side, so the revision stays in the user's voice and on-brand. Attached media and any existing schedule are preserved. Channels that carry their own tailored copy keep it: the revision changes the shared draft only. The words it replaces are kept in the post's version history, where the user can restore them in DemandBird.

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": {
      "id": "<id>",
      "feedback": "<feedback>"
    },
    "name": "revise_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesPost ID of the draft to revise: the post_id returned by draft_post / save_draft / list_drafts
feedbackYesWhat the user wants changed, in their own words. Pass their message through; don't rewrite it into instructions.
platformNoOptional: the platform whose length limit the revision should fit. Defaults to the post's first platform. Does not change which channels the post publishes to.
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 revise with what it has instead of asking for more context.

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

A4.4/5.0
Behavior4/5

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

Annotations only declare this is a non-read-only, non-destructive, closed-world mutation; the description goes well beyond that by disclosing that attached media and existing schedules are preserved, that replaced wording remains restorable in version history, that channel-specific copy is not overwritten, and that a server-side voice engine runs. It stops short of stating what the response contains or what happens if the draft is already published/queued, which is the one meaningful gap.

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 the action and the routing rule, and most sentences carry distinct information (media/schedule preservation, version history, channel copy). The opening line and the following sentence overlap heavily ('Rewrite an existing post from the user's feedback, with AI' versus 'Apply the user's feedback to an EXISTING draft'), so one of them is redundant.

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 non-destructive mutation with no output schema, annotations present, and full schema coverage, the description covers everything an agent needs: what it mutates, what is preserved, where the old content goes, and which sibling not to use instead. Residual gaps are minor.

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 every parameter including the platform enum and the workspace scoping note is already documented in the schema. The description adds context about the server-side voice engine and preservation rules but contributes no new meaning to individual parameters beyond what the schema already says.

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 ('Apply the user's feedback to an EXISTING draft and save the revision onto the SAME post') and makes the key scoping point that the revision lands on the original post rather than a new one. An agent can tell it apart from draft_post without inspecting either 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 an explicit trigger ('Use this every time the user reacts to a draft you already produced') with concrete examples of user phrasing, plus an explicit negative rule ('Do NOT call draft_post again to act on feedback') that names the wrong alternative and the consequence of using it. The tailored-channel clause also implicitly separates it from per-channel tailoring.

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