Compass OS: Career

add story

add_story

Save a new interview story to the user's story bank in STAR form (situation, task, action, result), in their words, tagged with competencies: leadership, influence, conflict, failure, metrics, strategy, prioritization, execution, customer, team, ai-ml. Read list_stories first so a story isn't saved twice; a dated result belongs in the wins log instead. It asks the user first and only adds: saving it twice makes two stories. Changing a story happens in the story bank in Compass OS. Returns the saved story. 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": {
      "title": "<title>",
      "situation": "<situation>",
      "action": "<action>",
      "result": "<result>"
    },
    "name": "add_story"
  }
}

Input Schema

Name	Required	Description
`tags`	No	The competencies it shows
`task`	No	STAR task: what the user was responsible for; may be empty
`title`	Yes	A short name for the story, e.g. "Rescuing the Q3 launch"
`action`	Yes	STAR action: what the user did, in the first person
`result`	Yes	STAR result: what came of it, ideally with a number
`situation`	Yes	STAR situation: the context and the problem

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"
+}

Changed7 schema fields changedNov 4, 2026

addedInput schema / properties / action / description

Added value: +"STAR action: what the user did, in the first person"

addedInput schema / properties / result / description

Added value: +"STAR result: what came of it, ideally with a number"

addedInput schema / properties / situation / description

Added value: +"STAR situation: the context and the problem"

addedInput schema / properties / tags / description
```
Added value: +"The competencies it shows"
```

addedInput schema / properties / task / description

Added value: +"STAR task: what the user was responsible for; may be empty"

addedInput schema / properties / title / description

Added value: +"A short name for the story, e.g. \"Rescuing the Q3 launch\""

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

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=false and idempotentHint=false, but the description adds the operational meaning of that: 'It asks the user first and only adds: saving it twice makes two stories.' It further discloses the reversibility window ('undo can put it back within 24 hours') and the response ('Returns the saved story'), which are not derivable from the annotation flags alone.

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 most important constraints (dedupe check, wins-log alternative) are front-loaded in the first two sentences, and the STAR expansion plus undo window are cheap context. The long inline competency list restates the schema enum and could be dropped without loss, which keeps it from a 5.

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 six-parameter mutation with a confirmation prompt and an output schema, the description covers the costly failure modes: duplicate creation, misrouting dated results, and attempting edits here. Return values need not be explained since an output schema exists, yet the one-line mention is enough to set expectations.

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 coverage is 100%, so every parameter is already documented, and the description's enumeration of the eleven competency tags largely duplicates the enum in the schema rather than explaining how to choose among them. It adds some genuine guidance — stories should be 'in their words' — but that is thin against a fully described schema, so 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?

The description opens with a specific verb and resource ('Save a new interview story to the user's story bank') and pins the artifact format (STAR), so the agent knows exactly what is produced. It also explicitly separates this tool from two neighbors: list_stories (dedupe check) and the wins log (dated results).

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 a concrete precondition ('Read list_stories first so a story isn't saved twice'), a routing rule away from this tool ('a dated result belongs in the wins log instead'), and an exclusion for editing ('Changing a story happens in the story bank in Compass OS'). When-to-use, when-not-to-use, and the alternative destinations are all stated rather than implied.

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?