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

Annotations declare non-readOnly, non-idempotent, open-world, non-destructive; the description goes further by disclosing the asynchronous processing model ('Google processes a source before chat and Studio can use it... status ready'), the returned fields (id, title, kind, status), and the concrete duplicate-source risk on retry. That is exactly the context annotations cannot carry.

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-loaded with what the tool does, then the return shape, then the sibling exclusion, then the retry hazard — each in a single dense clause with no filler. The trailing 'POST /sources' is the only near-redundant element and is trivial.

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?

No output schema exists, and the description compensates by naming the returned fields and the status lifecycle the agent must poll. Combined with the retry warning and the sibling routing, an agent has everything needed to call this correctly on the first attempt.

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 baseline is 3, but the description adds a real constraint the schema cannot express: at least one source-bearing parameter must be supplied even though only 'notebook' is required. It also states the 1-50 URL ceiling and that YouTube links are auto-classified, reinforcing rather than duplicating schema text.

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 ('Add sources to a notebook in one call') and enumerates the accepted source kinds: URLs/YouTube, pasted text, Drive files, Play Books ebooks. It explicitly names the sibling it is not (notebook_upload_source for file uploads), so the boundary is unambiguous.

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?

Gives the selection rule against the alternative ('For a file (PDF, audio, image...) use notebook_upload_source') and an in-band constraint ('give at least one'). It also prescribes a timeout recovery procedure ('check notebook_get_notebook before retrying, or sources may be added twice'), which is explicit when-and-how guidance.

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