TechFabric

Quiz me on a post

quiz_me

Read-onlyIdempotent

Interactive: a multiple-choice quiz from a published post's own FAQs: each question is one of its FAQs, the right option is the post's answer, and the others are answers the site gives to other questions; no model writes them. Each has its answer, the post's explanation and a link. With form: true, a client that shows forms asks the questions in one and scores it; a host with MCP Apps scores it in its view; otherwise the text lists the questions and the key: ask the reader before revealing it, then send their letters as answers to score. A reader who kept a resume code (Keep my progress, in a host without Fabric's view state) picks up with resume alone. For example: "quiz me on this post", "test what I learned", "check my understanding".

Input Schema

Name	Required	Description
`form`	No	true: in a client that shows forms and no MCP Apps view, ask the reader the questions in a form and return the score. Send it only when the reader wants to answer in a form; left out, the quiz comes back unanswered
`post`	No	A post with FAQs: its URL or slug, or the topic to find one on. Not needed with resume
`resume`	No	A resume code the reader kept from an earlier quiz (it starts kp1.): picks up where they left off. The code names its post, so nothing else is needed
`answers`	No	The reader's answers, one per question in order: a letter (A to D) or a 0-based index. Sent, the quiz comes back scored

Output Schema

Name	Required	Description
`keep`	No	For an interactive view: what its Keep my progress button makes a resume code from (scope), and the reader's place when a resume code was sent (resumed). No personal data; nothing is stored on the server.
`kind`	Yes
`note`	Yes
`page`	Yes
`total`	Yes
`scored`	Yes
`questions`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 27, 2026

changedInput schema / properties / form / description

Previous value: -"false: never ask in a form; return the questions as text"New value: +"true: in a client that shows forms and no MCP Apps view, ask the reader the questions in a form and return the score. Send it only when the reader wants to answer in a form; left out, the quiz comes back unanswered"

Changed4 schema fields changedOct 27, 2026

changedInput schema / properties / post / description

Previous value: -"A post with FAQs: its URL or slug, or the topic to find one on"New value: +"A post with FAQs: its URL or slug, or the topic to find one on. Not needed with resume"

addedInput schema / properties / resume

Added value: +{
+  "description": "A resume code the reader kept from an earlier quiz (it starts kp1.): picks up where they left off. The code names its post, so nothing else is needed",
+  "maxLength": 600,
+  "minLength": 5,
+  "pattern": "^kp1\\.[A-Za-z0-9_-]+$",
+  "type": "string"
+}

removedInput schema / required
```
Removed value: -[
-  "post"
-]
```

addedOutput schema / properties / keep

Added value: +{
+  "description": "For an interactive view: what its Keep my progress button makes a resume code from (scope), and the reader's place when a resume code was sent (resumed). No personal data; nothing is stored on the server.",
+  "properties": {
+    "kind": {
+      "type": "string"
+    },
+    "resumed": {
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "scope": {
+      "type": "string"
+    },
+    "stale": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "kind",
+    "scope",
+    "resumed",
+    "stale"
+  ],
+  "type": [
+    "object",
+    "null"
+  ]
+}

Changed2 schema fields changedOct 24, 2026
- addedInput schema / properties / answers / items / anyOf
```
Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "integer"
+  }
+]
```
- removedInput schema / properties / answers / items / type
```
Removed value: -[
-  "string",
-  "integer"
-]
```
AddedOct 23, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly/idempotent/non-destructive), and the description still adds real behavioral context: the quiz is answered in one of three modes (form, MCP Apps view, or plain text with the key withheld until the reader has answered), answers are scored on submit, and a stored resume code lets a reader pick up where they left off. It also discloses a non-obvious trait — the questions and answers are sourced from the post itself rather than generated — which an agent could not infer from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded and every clause arguably carries information, but the middle sentences are run-ons that stack parentheticals ('Keep my progress, in a host without Fabric's view state'), which makes the mode-selection rules hard to parse on a single read. The content earns its place; the packaging does not.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained, yet the description still tells the agent that each question carries its answer, explanation and link. The main residual ambiguity is whether text mode requires one call (questions) followed by a second call with answers, or whether the unanswered-then-scored flow is returned from a single call — the description implies but does not state this.

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 3 would be the baseline; the prose goes beyond the per-parameter descriptions by explaining how the parameters combine — resume alone suffices ('the code names its post, so nothing else is needed'), answers are sent in question order as letters, and form is only for form-capable clients. That interaction logic is not spelled out 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 first sentence states a specific verb and resource: 'a multiple-choice quiz from a published post's own FAQs', and then defines the question/answer provenance exactly ('each question is one of its FAQs, the right option is the post's answer, and the others are answers the site gives to other questions; no model writes them'). No sibling tool does anything similar, so it is trivially distinguishable from the rest of the toolset.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit invocation triggers ('quiz me on this post', 'test what I learned', 'check my understanding') and conditions the form parameter on 'a client that shows forms and no MCP Apps view'. It does not name any sibling alternative or exclusion (e.g., when to use explore_post or ask_author instead), so it stops just short of the top mark.

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

All TechFabric 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.