Skip to main content
Glama

Get the aidemo authoring guide

get_authoring_guide
Read-only

Fetches the canonical demo-authoring guide and topic-specific slices before you create or edit a storyboard, so you follow the correct schema and action vocabulary.

Instructions

The canonical guide to authoring demos: storyboard schema, action vocabulary, demo-director principles, ChatGPT-app recording facts. Call this FIRST before authoring or editing a storyboard. Pass topic (core | schema | polish | attention | chatgpt-apps | stills | variants | captions | debug | troubleshooting | ci, or any H2 heading prefix) for one slice instead of the whole ~1000-line guide; start with core, then fetch attention/polish/chatgpt-apps as needed.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_authoring_guide"
  }
}

Input Schema

NameRequiredDescriptionDefault
topicNoSlice: core, schema, polish, attention, chatgpt-apps, stills, variants, captions, debug, troubleshooting, ci — or an H2 heading prefix. Omit for the full guide.

Output Schema

NameRequiredDescriptionDefault
guideYes
topicNo
topicsYes
sectionsYes
engineVersionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.20.2
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • changedInput schema / properties / topic / description
      Previous value: -"Slice: core, schema, polish, attention, chatgpt-apps, stills, variants, captions, debug, ci — or an H2 heading prefix. Omit for the full guide."New value: +"Slice: core, schema, polish, attention, chatgpt-apps, stills, variants, captions, debug, troubleshooting, ci — or an H2 heading prefix. Omit for the full guide."
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed6 schema fields changedv0.14.1
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / topic
      Added value: +{
      +  "description": "Slice: core, schema, polish, attention, chatgpt-apps, stills, variants, captions, debug, ci — or an H2 heading prefix. Omit for the full guide.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / sections
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / topic
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / topics
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "guide",
      -  "engineVersion"
      -]New value: +[
      +  "guide",
      +  "engineVersion",
      +  "topics",
      +  "sections"
      +]
  3. First observedv0.9.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true, so the safety profile is covered externally. The description adds genuinely useful behavioral context the annotations cannot: the guide is ~1000 lines, omitting topic returns the whole thing, and passing a topic returns one slice. It does not discuss caching or rate limits, but for a static doc read that is minor.

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?

Three front-loaded sentences: purpose, priority instruction, then parameter strategy. The topic list duplicates the schema description, costing some space, but the cost warning (~1000 lines) and sequencing advice justify the density.

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 single-optional-parameter read tool with an output schema and a readOnly annotation, nothing an agent needs is missing: what it contains, when to call it, how to slice it, and the recommended first topic are all present.

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% and the topic enum-like list is already in the schema, so the baseline is 3. The description earns above baseline by explaining intent behind the parameter — slice vs. full guide — and by prescribing a reading order (core first), which is meaning the schema does not carry.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource ('the canonical guide to authoring demos') and enumerates its contents: storyboard schema, action vocabulary, demo-director principles, and ChatGPT-app recording facts. It is clearly distinguishable from most siblings, though it does not explicitly say how it differs from get_storyboard_schema, which overlaps its 'schema' topic.

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 states an explicit ordering rule ('Call this FIRST before authoring or editing a storyboard') and a recommended fetch sequence ('start with core, then fetch attention/polish/chatgpt-apps as needed'). When-to-use and how-to-progress are both spelled out with no inference required.

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