download_artifact

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

With zero annotations, the description carries the full burden and delivers: downloads are sandboxed to the download directory and outside paths are refused; default location (~/Downloads/gemini-notebook) and NOTEBOOKLM_DOWNLOAD_DIR override are disclosed; polling semantics (wait, wait_timeout, poll_interval) are explained; and artifact_id falls back to 'latest' when omitted. This is far more than the schema or annotations reveal.

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 one-sentence purpose is front-loaded, followed by a positioning statement and a compact type list. The Args block is organized per-parameter with defaults and formats, and the Returns line plus three varied examples close it out. For a 9-parameter tool with no schema descriptions, every sentence earns its place.

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?

Every one of the 9 parameters is documented with defaults, allowed values, and behavioral notes; the path-confinement constraint and polling knobs are covered; and since an output schema exists, the brief 'Returns: dict with status and saved file path' suffices. Nothing an agent needs to invoke this complex tool correctly is missing.

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 must compensate — and it does comprehensively. artifact_type maps each value to its format (audio→MP4/MP3, report→Markdown, etc.), output_path explains relative pathing and confinement, output_format and slide_deck_format get explicit value lists and defaults, and every optional parameter's behavior is described. Three usage examples ground the semantics concretely.

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?

Opens with a specific verb+resource: 'Download any NotebookLM artifact to a file.' The next sentence, 'Unified download tool replacing 9 separate download tools,' explicitly positions it against the per-type download tools an agent might otherwise reach for. The full artifact-type list removes any ambiguity about scope.

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?

'Unified download tool replacing 9 separate download tools. Supports all artifact types' gives clear context that this is the single entry point for downloading any one artifact. However, it does not explicitly say when to prefer the sibling download_all_artifacts or export_artifact, so the when-not-to-use guidance is left to inference.

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