nblm-mcp

generate_artifact

Generate Studio artifacts like podcasts, reports, quizzes, or mind maps from a notebook's sources. Runs server-side; poll with list_artifacts for status.

Instructions

Generate a Studio artifact (podcast, report, quiz, mind map...).

Generation runs server-side and is slow — an audio overview commonly takes several minutes — and it consumes the account's daily Studio quota. Prefer the default wait=false and poll with list_artifacts.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`kind`	Yes	One of audio, video, report, study_guide, quiz, flashcards, infographic, slide_deck, mind_map.
`wait`	No	Block until the artifact is ready (or the configured timeout elapses) instead of returning as soon as it is queued.
`language`	No	BCP-47 language code for the output, e.g. "en", "es".	en
`quantity`	No	quiz/flashcards only — fewer, standard, or more.
`difficulty`	No	quiz/flashcards only — easy, medium, or hard.
`source_ids`	No	Restrict generation to these sources. Omit to use all.
`notebook_id`	Yes	Notebook whose sources feed the generation.
`audio_format`	No	audio only — deep_dive, brief, critique, or debate.
`audio_length`	No	audio only — short, default, or long.
`instructions`	No	Free-text steer for the output ("focus on the pricing section", "explain it for beginners").
`report_format`	No	report only — briefing_doc, study_guide, or blog_post.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 12, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does well: it discloses that generation is server-side, slow (audio can take minutes), and consumes the account's daily Studio quota. It stops short of covering auth requirements or failure behavior when the quota is exhausted.

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

Conciseness5/5

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

Four tight sentences: purpose first, then cost/latency, then the recommended call pattern. Every sentence carries load and nothing is repeated from the schema.

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?

An output schema exists so return values needn't be explained, and all 11 parameters are schema-documented; the description supplies the missing quota and latency context plus the preferred invocation pattern. Only auth/prerequisite and failure-mode details are absent.

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 every parameter (including wait, kind, and the kind-conditional options) is already documented in the schema. The description adds meaning to wait by pairing it with the polling workflow, but adds nothing else beyond 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?

States a specific verb (Generate) and resource (Studio artifact) and enumerates concrete artifact types (podcast, report, quiz, mind map), which lets an agent distinguish it from sibling read tools like list_artifacts and download_artifact.

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?

Gives explicit operational guidance: prefer wait=false and poll with list_artifacts rather than blocking. It names the alternative tool and the condition that selects it, but says nothing about when NOT to use this tool (e.g., versus ask).

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

Deploy Server