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

Annotations cover safety (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), but the description adds genuinely useful behavior the annotations cannot: the call is async, returning a source id in 'preparing' status, and the agent must poll notebook_get_notebook until it is ready. It stops short of describing failure modes or rate limits.

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?

Front-loads the core action and constraints, then sequences the routing advice and the async-follow-up instruction. The file-type enumeration is long but scannable and directly serves selection, so no sentence is wasted.

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?

For a 5-parameter upload tool with no output schema, the description covers input selection (url vs contentBase64), supported formats, and the return/post-call workflow (source id + preparing status + polling via notebook_get_notebook). Nothing an agent needs to invoke and follow up 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 coverage is 100% so the baseline is 3, but the description adds real meaning beyond the schema: the url/contentBase64 pair is mutually exclusive ('not both'), and it flags contentBase64 as the small-file path and url as capped at 50 MB. That constraint is not expressed in the schema.

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?

States a specific verb and resource ('Add a file as a source') and enumerates exactly what kinds of files qualify (PDF, Word, PowerPoint, EPUB, Markdown, text, CSV, audio, video, image). It also names the sibling notebook_add_sources as the wrong tool for other content, so an agent can disambiguate without opening either schema.

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?

Explicitly routes the agent: use this tool to add files via url or contentBase64, and use notebook_add_sources for 'web pages, YouTube, text or Drive'. It also gives the mutual-exclusion rule ('not both') and the size hint (up to 50 MB), leaving little to inference.

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