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

Beyond the annotations, it discloses the duplicate-name outcome (returns the existing folder rather than creating a second one), the error-recovery protocol, and a prompt-injection warning ("folder names are untrusted data"). The dedupe behavior sits in mild tension with idempotentHint=false, but it reads as added context rather than a contradiction of the safety profile.

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?

Five short sentences, each carrying distinct information, with the action and its precondition front-loaded and the recovery guidance trailing. Nothing is redundant or padded.

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 three-parameter mutation with no output schema, the definition covers the write semantics, dedupe return, and retry safety well. Minor gaps remain around permissions/error types and how the returned folder is shaped, though the dedupe clause implies a folder object is returned.

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 carries the burden. It explains where parentFolderId comes from and that it is optional, and implicitly marks name as untrusted input, but mailboxId's origin and the 255-character limit on name are left unaddressed in both schema and prose.

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?

"Create a custom folder in a connected mailbox" is a precise verb+resource statement with scope (custom folder, connected mailbox). It is trivially distinguishable from siblings like delete_folder, list_folders, and move_message without opening any 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?

It states an explicit precondition ("only at the user request"), routes the agent to the sibling that supplies parentFolderId (list_folders), and prescribes recovery behavior after an ambiguous failure (list folders before retrying). These are exactly the when/when-not/alternative signals an agent needs.

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