ppt-generator

Overview Schema Source Related Servers Discussions Admin

prepare_design_doc_draft

Prepares the client prompt to draft a shared design intent before slides, returning skip if one already exists. Use it once to keep theme and narrative consistent across all slides.

Instructions

Prepares the prompt for the CLIENT to draft DESIGN.md (design intent).

No LLM call. If DESIGN.md already exists, returns {"skip": true} — reuse the existing design intent (do not regenerate). Otherwise returns system_prompt, user_prompt, response_schema, and project_id. Generate the draft JSON (theme + tone + anti_slop + page_requests) matching response_schema, then call ingest_design_doc_draft.

Call this ONCE before generating slides, so every slide shares one design theme and narrative arc.

Args: project_id: Project ID. Loads outline from the saved project. outline_json: Full outline JSON. Optional if project_id is given. color_theme: Color theme ("dark" or "light", default: "dark").

Returns: JSON with system_prompt, user_prompt, response_schema, project_id, color_theme — or {"skip": true}.

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": "prepare_design_doc_draft"
  }
}

Input Schema

Name	Required	Default
`project_id`	No
`color_theme`	No	dark
`outline_json`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.7.0Jul 10, 2026

TDQS

A4.7/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does most of it: it discloses that no LLM call occurs, that a pre-existing DESIGN.md short-circuits to {"skip": true}, and what the success payload contains. It stops short of stating that the tool performs no writes at all (an agent must infer pure-read behavior from 'prepares the prompt'), so not a 5.

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?

Front-loaded with the core purpose and the skip condition, then the workflow instruction, then Args/Returns. The Returns section partly repeats the skip behavior and payload fields already stated in the body, which is mild redundancy, but every other sentence carries distinct, decision-relevant information.

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 three-parameter prep tool in a multi-step pipeline, nothing an agent needs is missing: input sourcing, the skip/caching rule, the required downstream call to `ingest_design_doc_draft`, and the response shape. The existence of an output schema makes the explicit return listing a bonus rather than a necessity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate and it does fully: project_id is explained as 'Loads outline from the saved project', outline_json is described as the full outline JSON that is 'Optional if project_id is given' (capturing the real mutual-exclusivity rule), and color_theme gains the enum values "dark"/"light" plus the default that the schema omits.

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 and artifact: prepares the prompt for the CLIENT to draft DESIGN.md (design intent), and explicitly distinguishes itself from the actual ingestion step by naming `ingest_design_doc_draft` as the follow-up. 'No LLM call' further pins down that this tool only assembles inputs, separating it from `prepare_design_slide` and the other prepare_* siblings.

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?

Gives explicit timing ('Call this ONCE before generating slides'), an explicit when-not ('If DESIGN.md already exists, returns {"skip": true} — reuse the existing design intent (do not regenerate)'), and an explicit next action ('Generate the draft JSON ... then call `ingest_design_doc_draft`'). The rationale (one shared theme and narrative arc) explains why the once-only constraint exists.

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