Compass OS: Career

create draft

create_draft

Save a new LinkedIn draft to Brand studio in the user's words: the text, a short topic, and a kind (lesson, win, take, question). Use edit_draft to change a draft that's already there, and update_linkedin for the LinkedIn headline or About. Every claim is checked against the profile, and unbacked ones are counted in the reply. It asks the user first and only adds a draft: saving twice makes two, nothing is scheduled, and Compass OS never 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": {
      "text": "<text>"
    },
    "name": "create_draft"
  }
}

Input Schema

Name	Required	Description
`kind`	No	What sort of piece it is; leave empty for lesson
`text`	Yes	The draft's full text in the user's words, at most 3000 characters
`topic`	No	A short topic Brand studio lists it by, e.g. "Shipping the new onboarding"

Output Schema

Name	Required	Description
`text`	Yes	The answer, or what was done, in plain words for the user: the same text as content
`undo`	No	On a saved write: its undo handle, for undo within 24 hours
`widget`	No	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

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026

addedOutput schema / properties / undo

Added value: +{
+  "description": "On a saved write: its undo handle, for undo within 24 hours",
+  "type": "string"
+}

Changed4 schema fields changedNov 4, 2026

addedInput schema / properties / kind / description

Added value: +"What sort of piece it is; leave empty for lesson"

addedInput schema / properties / text / description

Added value: +"The draft's full text in the user's words, at most 3000 characters"

addedInput schema / properties / topic / description

Added value: +"A short topic Brand studio lists it by, e.g. \"Shipping the new onboarding\""

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"
+}

First observedNov 4, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only say it is a non-idempotent, non-destructive write. The description adds substantial context beyond that: it asks the user first, creates duplicates if called twice, schedules nothing, never posts, checks claims against the profile and counts unbacked ones, and can be undone within 24 hours.

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-loads the action and destination, then moves to alternatives, side effects, and undo. It is dense but every sentence carries information; the claims-checking aside is the only part that could be trimmed.

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?

An output schema exists, so return values needn't be explained. The description covers the confirm step, idempotency behavior, scheduling/posting constraints, and reversibility window, which is everything an agent needs to call this mutation safely.

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 the baseline is 3. The description still adds some meaning by framing the text as 'in the user's words' and listing the kinds as lesson, win, take, question, matching the enum-free schema; it does not add format or length detail beyond the schema, so it stays modestly above baseline.

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 (save/create) and resource (a new LinkedIn draft) and names the destination (Brand studio) plus the inputs it captures. It also explicitly names edit_draft and update_linkedin as the tools for other jobs, so an agent can separate it from siblings without reading a 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 routing: use edit_draft to change an existing draft, update_linkedin for the headline or About. It also warns that saving twice creates two drafts, which tells the agent when not to call it again.

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 tools Inspect

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

Need Help?