Skip to main content
Glama
Sign In

Compass OS: Career

by dev.compass-os
OverviewDiscussionsAdmin

make interview prep

make_interview_prep
Destructive

Make, or remake, a tracked role's interview prep (likely questions matched to the user's stories, questions to ask, a 30-60-90 plan), its company research (reading the company's own site and the posting: what the role cares about, where the background fits), or both, and save them on the job's Interview tab in place of what was there. Read what's saved with get_interview_prep first. The role needs its posting text (tracking it again with its link adds it). It asks the user first, uses their AI, and research can take a minute. Returns the new prep. 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": {
      "company": "<company>",
      "make": "<make>"
    },
    "name": "make_interview_prep"
  }
}

Input Schema

NameRequiredDescriptionDefault
makeYesWhat to make: prep (questions and plan), research (the company), or both
titleNoThe role's title as the pipeline lists it; leave it empty when the user named only the company
companyYesThe employer's name, e.g. "Stripe"

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
    • addedOutput schema / properties / undo
      Added value: +{
+  "description": "On a saved write: its undo handle, for undo within 24 hours",
+  "type": "string"
+}
  2. Changed4 schema fields changed
    • addedInput schema / properties / company / description
      Added value: +"The employer's name, e.g. \"Stripe\""
    • addedInput schema / properties / make / description
      Added value: +"What to make: prep (questions and plan), research (the company), or both"
    • changedInput schema / properties / title / description
      Previous value: -"The role's title; leave it empty when the user named only the company"New value: +"The role's title as the pipeline lists it; leave it empty when the user named only the company"
    • 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"
+}
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, and the description corroborates rather than contradicts them by spelling out exactly what is destroyed ("save them on the job's Interview tab in place of what was there"). It adds behavior the annotations cannot express: a user confirmation step, use of the user's own AI, an expected latency ("research can take a minute"), and a 24-hour undo window.

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?

The first sentence is heavy with parentheticals but front-loads the two output modes, and the following short sentences each carry a distinct operational fact (read first, prerequisite, latency, return, undo). Slightly dense, but nothing is 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?

Given an output schema exists, the description need not detail return shape, and its brief "Returns the new prep" suffices. Prerequisites, overwrite semantics, confirmation behavior, latency, and reversibility are all covered, leaving no operational gap for a destructive open-world write.

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 the enum values for make and the title/company guidance are already documented in the schema. The description adds only a prerequisite about posting text, not per-parameter meaning, so the baseline 3 applies.

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 (make/remake) and resource (interview prep and/or company research), enumerates the contents of each artifact (likely questions matched to stories, questions to ask, 30-60-90 plan; site and posting reading), and names the sibling that reads rather than writes (get_interview_prep). An agent can distinguish this from get_interview_prep without opening any 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?

Explicit sequencing ("Read what's saved with get_interview_prep first"), a precondition ("The role needs its posting text (tracking it again with its link adds it)"), and a reversal path ("undo can put it back within 24 hours"). It also flags that the user is prompted first, which tells the agent this is not a silent background write.

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