Skip to main content
Glama
Sign In

Compass OS: Career

by dev.compass-os
OverviewDiscussionsAdmin

edit draft

edit_draft
DestructiveIdempotent

Replace the full text of one Brand studio draft with the user's edit, naming the draft by its topic or opening words as list_brand_posts shows them. Use create_draft for a new draft. Every claim is checked against the profile again. It asks the user first; a scheduled draft keeps its time, and Compass OS never posts. If the draft changed in Brand studio meanwhile, nothing is saved and the reply says to read it again with list_brand_posts. Once it's saved, undo can put it back within 24 hours.

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": {
      "draft": "<draft>",
      "text": "<text>"
    },
    "name": "edit_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe draft's whole new text, at most 3000 characters
draftYesWhich draft: its topic, or its opening words, as list_brand_posts shows them

Output Schema

NameRequiredDescriptionDefault
textYesThe answer, or what was done, in plain words for the user: the same text as content
undoNoOn a saved write: its undo handle, for undo within 24 hours
widgetNoThe card the host draws with it, e.g. "pipeline"; "confirm" means a write waits for the user's Yes and nothing is saved yet

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / draft / description
      Previous value: -"Which draft: its topic, or its opening words, as brand shows them"New value: +"Which draft: its topic, or its opening words, as list_brand_posts shows them"
  2. Changed1 schema field changed
    • addedOutput schema / properties / undo
      Added value: +{
+  "description": "On a saved write: its undo handle, for undo within 24 hours",
+  "type": "string"
+}
  3. Changed3 schema fields changed
    • addedInput schema / properties / draft / description
      Added value: +"Which draft: its topic, or its opening words, as brand shows them"
    • addedInput schema / properties / text / description
      Added value: +"The draft's whole new text, at most 3000 characters"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "text": {
+      "description": "The answer, or what was done, in plain words for the user: the same text as content",
+      "type": "string"
+    },
+    "widget": {
+      "description": "The card the host draws with it, e.g. \"pipeline\"; \"confirm\" means a write waits for the user's Yes and nothing is saved yet",
+      "type": "string"
+    }
+  },
+  "required": [
+    "text"
+  ],
+  "type": "object"
+}
  4. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Substantially exceeds the annotations: it discloses that the user is asked first, that every claim is re-checked against the profile, that a scheduled draft retains its time, that nothing is ever posted, that a concurrent change in Brand studio silently aborts the save, and that a 24-hour undo window exists. These are exactly the consequences an agent needs before invoking a destructiveHint mutation.

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 draft-addressing rule, then follows with consequences in short, information-dense clauses. No sentence is filler, though the run of five independent clauses reads as a list rather than a prioritized structure.

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 two-parameter destructive mutation with full schema coverage and an output schema, the description covers the decision-relevant surface: confirmation, conflict handling, scheduling side effects, and reversibility. Nothing needed to call it correctly or to anticipate its reply is missing.

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%, so both parameters are already documented, which sets the baseline at 3. The description adds a little value by reinforcing that the replacement is wholesale ('full text') and by repeating the draft-addressing convention with a pointer to list_brand_posts, making the identifier's expected form concrete.

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 precise verb and resource ('Replace the full text of one Brand studio draft with the user's edit') and adds the non-obvious addressing method ('naming the draft by its topic or opening words as list_brand_posts shows them'). It also explicitly contrasts with create_draft, so an agent can distinguish it from the creation path without opening another 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?

Names a concrete alternative and the condition that selects it: 'Use create_draft for a new draft.' It also tells the agent what to do on a conflict — 'read it again with list_brand_posts' — which is the operational fallback path an agent needs.

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

All Compass OS: Career toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources