notebook_add_source

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

No annotations exist, so the description carries the full burden. It does disclose non-obvious behavior: an engine selector ('auto', 'gcp_rest', 'rpc_bridge') and a `wait` flag that blocks on source indexing completion — genuinely useful context an agent could not infer. It omits mutation/irreversibility, auth requirements implied by the notebook_login sibling, duplicate-source handling, and side effects on the target notebook, which is a real gap for an unannotated write tool.

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 purpose sentence is correctly front-loaded and each Args line is short and earns its place. There is minor duplication — the supported source kinds are enumerated in the opening sentence and again in the source_type entry — and the raw Python docstring formatting is slightly heavier than needed, but nothing is bloated.

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?

The output schema exists, so return values need not be explained. However, with zero annotations and zero schema description coverage on an 8-parameter mutation tool, the description should also establish required permissions/state and what happens to the notebook after insertion; it covers the mechanics but not the operating contract.

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% across 8 parameters, so the description must compensate and largely does — every parameter gets a line, including the conditional constraint that mime_type applies only when source_type == 'gdrive', and the default behavior of notebook_id falling back to the workspace-attached notebook. Two entries remain thin: `engine` lists the allowed values without saying which to choose or why, and 'workspace_dir override' does not explain what is being overridden.

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 (Add) and resource (source) with an explicit enumeration of supported source kinds: text, web URL, YouTube video, Google Drive document. That is far beyond a tautology. It does not, however, contrast itself with siblings such as notebook_sync_files, which plausibly also introduces content into a notebook, so the differentiation bar for a 5 is not met.

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?

Usage is implied by the source_type enumeration — an agent can infer this is the tool for registering one source at a time. But there is no explicit when-to-use versus notebook_sync_files (bulk file ingestion) or notebook_attach, and no prerequisites such as requiring a completed notebook_login or an existing notebook_id.

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