Baixa o conteúdo de um artifact. Texto (report/mind_map/quiz/flashcards/data_table) retorna inline em content; binário (audio/video/slide_deck/infographic) retorna metadados + tamanho (entrega por URL é tratada à parte).
Bulk support: accepts notebook_ids, artifact_ids for batched execution.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | Yes | ||
| artifact_id | No | ||
| notebook_id | Yes | ||
| artifact_ids | No | ||
| notebook_ids | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds beyond this by specifying that text returns inline content, binary returns metadata + size, and bulk support is available. It does not contradict annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two sentences covering the main behavior and bulk support. Every sentence adds value, and the information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 5 parameters (2 required) and no output schema, the description provides an adequate overview but lacks details on parameter formats, error handling, or specific return values. It mentions URL delivery separately but does not elaborate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description bears the burden. It explains that 'kind' determines content type and notes bulk parameters (artifact_ids, notebook_ids). However, it does not detail each parameter's format or constraints, leaving some ambiguity. It adds some value but not full compensation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool downloads an artifact's content, distinguishing between text types (inline content) and binary types (metadata + size). It also mentions bulk support with notebook_ids and artifact_ids, which distinguishes it from related sibling tools like notebooklm_artifact_get.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use the tool (downloading artifacts), with distinctions between inline text and binary content, and bulk execution. However, it does not explicitly state when not to use it or mention alternatives, but the context is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes (notebook vs source vs note vs artifact vs sharing). Minor overlap exists between notebooklm_ask and notebooklm_history (both Q&A-related) and between artifact generate/poll/retry, but descriptions help differentiate. Meta-tools like marketplace and authenticate are separate in function.
Core tools follow a consistent notebooklm_{resource}_{action} pattern. However, meta-tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) lack the notebooklm_ prefix, breaking overall naming consistency. Within the core domain, naming is predictable.
43 tools is high but covers a broad domain: notebooks, sources, notes, artifacts (multiple types), sharing, Q&A, plus meta-tools. Some tools could be merged (e.g., share_add/remove/update/view_level), and meta-tools inflate count. Feels slightly heavy but not excessive for the feature set.
Covers full lifecycle for notebooks, sources, notes, artifacts (CRUD plus generate, download, poll, retry, suggestions). Sharing and Q&A have comprehensive operations. Minor gap: no tool to update notebook metadata beyond rename, but overall very complete.