Skip to main content
Glama

Eurekuh

Edit a post that hasn't gone out

update_post
Destructive

Change a draft, scheduled, failed or unapproved post instead of cancelling and recreating it. Fields left out keep their value, and the new values pass the same checks as create_post. create_post makes one post per network, so edit each id. A scheduledAt on a draft or failed post schedules it. A post that is out can't be edited here; it has to be changed on the network. For the first comment, use set_first_comment. Off by default: the organization's owner must turn on AI editing in Organization settings, otherwise this is refused.

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>"
    },
    "name": "update_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe post id from create_post or list_posts.
mediaNoReplaces all the post's media: mediaId values from upload_media or upload_file. Empty removes it.
captionNoThe new caption. A line containing only "---" splits it into a thread.
topicTagNoThreads only: as in create_post. "" removes it.
visibilityNoAs in create_post.
scheduledAtNoISO 8601, in the future.
organizationIdNoWhich organization to act in: an id from list_organizations. Leave out for this connection's default organization.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the supplied mutation and destructive annotations, it discloses partial-update retention, create_post-equivalent validation, the scheduling side effect of scheduledAt, and the inability to edit published posts. The owner-controlled AI editing opt-in and refusal behavior are especially important prerequisites that could otherwise cause unexpected failures.

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?

The description is front-loaded with the editable states and core reason to use the tool, then moves through behavior, limitations, alternatives, and prerequisites in a logical order. Although dense, each sentence contributes distinct operational information without filler.

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 seven-parameter mutation without an output schema, it covers eligibility, partial updates, validation, scheduling, per-network scope, published-post exclusions, an alternative tool, and feature gating. Together with the fully described schema and behavioral annotations, this leaves no material gap likely to prevent correct selection or invocation.

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 100%, but the description still adds meaningful semantics: omitted fields retain their values, scheduledAt can transition a draft or failed post into a scheduled state, and ids are network-specific because create_post creates one post per network. Parameter-specific elaboration is selective rather than exhaustive, but the schema adequately documents the remaining fields.

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?

The description uses a specific mutation verb and identifies exactly which posts can be changed: draft, scheduled, failed, or unapproved. It distinguishes this operation from cancelling and recreating, editing an already-published post, and setting a first comment.

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?

It gives clear positive usage guidance—edit rather than cancel and recreate—and explicit exclusions for posts that are already out. It also routes first-comment changes to set_first_comment and explains that each per-network post id must be edited separately.

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