Import a Drive / OneDrive folder into the Library

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

Annotations only give a generic write/open-world/non-idempotent/non-destructive profile; the description adds substantial context beyond that: it downloads via the user's connected account, stores a durable Hermoso URL per file, and is bounded by the drive.file OAuth scope. It discloses real behavioral limits an agent must relay to a user — subfolders are not walked, Google-native docs have no file to download, oversized/unreadable files are returned by name rather than silently dropped, and OneDrive has no picker scope limit.

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?

Purpose is front-loaded in the first sentence and the escalating caveats follow in a sensible order. The folderId instruction is duplicated from the schema and the all-caps emphasis is heavy-handed, but nearly every sentence carries information an agent needs to explain outcomes to a user.

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?

With only three parameters and no output schema, the description covers everything an agent needs: source discovery, auth precondition, scope limitation, partial-failure reporting semantics, and what to do when nothing is returned. There is no output schema, so the description's explanation of skipped-item reporting and the picker link fills the return-value gap well.

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 100%, so the schema already explains provider, folderId sourcing, and the limit/skip behavior; baseline 3 applies. The description largely restates what the schema says about folderId (source tool, omit for root) rather than adding new semantics, though the drive.file explanation meaningfully explains why folderId may yield nothing.

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 opening sentence names a specific verb (pull/import), a specific source (a Google Drive or OneDrive folder), and a specific destination (this profile's Library), then lists concrete downstream uses (publish, schedule, clone, product photo, reference). It is clearly distinguishable from the discovery siblings (list_drive_files / list_onedrive_files) and from the save_to_* tools by direction of data flow.

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?

It explicitly routes the agent to list_drive_files / list_onedrive_files with onlyFolders to obtain folderId, says to omit folderId for the root, and gives concrete follow-up instructions when a folder comes back empty. It also states the key precondition (user's own connected account is required because the file is not public). What it lacks is an explicit exclusion, e.g. when to prefer upload_file or get_drive_file instead of importing.

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