Compass OS: Career

confirm write

confirm_write

Destructive

Carry out or cancel a write the user was asked to confirm. Only the confirm card calls it, with the held write's ticket and the user's Yes or No; the model can't. Yes runs the held write once (a used or expired ticket fails), and No changes nothing. If the write fails, the ticket is kept so the card shows why and its Yes can try again. Returns what was saved.

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": {
      "ticket": "<ticket>",
      "approve": "<approve>"
    },
    "name": "confirm_write"
  }
}

Input Schema

Name	Required	Description	Default
`ticket`	Yes	The held write's ticket, from the confirm card
`approve`	Yes	true for the user's Yes, false for No

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"
+}

Changed3 schema fields changedNov 4, 2026

addedInput schema / properties / approve / description

Added value: +"true for the user's Yes, false for No"

addedInput schema / properties / ticket / description

Added value: +"The held write's ticket, from the confirm card"

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

A4.7/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the description earns credit for what it adds: single-use tickets, expiry causing failure, and No being a no-op. The failure-retention rule (ticket kept so a retry is possible) is exactly the kind of state behavior annotations cannot express. It stops just short of describing permissions or return payload shape, though the output schema covers the latter.

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?

Four sentences, each carrying distinct information: purpose, caller restriction, outcome semantics, and failure behavior. The most decision-relevant constraint (the model can't call it) is placed early, and nothing is repeated from the annotations or schema.

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 mutation tool, the description covers the caller, the idempotency/expiry model, the two outcomes, and the failure path. Return values need not be explained because an output schema exists, and the one clause 'Returns what was saved' is a sufficient pointer to it.

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, and the description goes slightly beyond by tying 'ticket' to the confirm card and its one-shot nature and by framing 'approve' as the user's Yes or No rather than a raw boolean. That is real added meaning, but the mechanics of both params are already largely in the schema.

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 states a specific pair of verbs (carry out or cancel) on a specific resource (a held write awaiting confirmation), and scopes it further by naming the single caller. No sibling tool in the list deals with a pending write, so the agent would not confuse this with edit_draft, delete_win, or undo.

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 an explicit exclusion — 'Only the confirm card calls it ... the model can't' — which tells the agent both when this tool is used and that it must not be invoked directly. The Yes/No outcomes are also spelled out, so the correct path is unambiguous.

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?