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

Annotations already declare a non-read-only, non-destructive, non-idempotent operation; the description adds real context on top: the operation is non-idempotent in practice ('Each call creates another folder, even with the same name'), and top-level creation is restricted to org owners/admins. It does not cover the idempotencyKey retry semantics, but the schema does, so the remaining gap is small.

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?

Three sentences, front-loaded with the verb and outcome, with no filler. The first sentence is dense and its colon-and-clause construction ('at the top level, which only owners and admins of the organization may, or inside a folder...') takes a reread, which costs it a point.

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 nested-body mutation tool with no output schema, the definition covers permissions, placement, duplication behavior, and downstream usage. It stops short of saying what is returned (presumably the new folder's id), which an agent needs to chain into updateReport, but that is a minor omission.

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 50% (body has no top-level description; idempotencyKey is fully documented in-schema). The description reinforces parentFolderId permission semantics that the schema already states, but it does add genuinely new meaning about the name field — that names need not be unique, so a name collision is not an error. That is useful but modest value beyond 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 ('Creates a folder'), plus ownership scope ('owned by the user') and the two legal placements (top level vs. inside a folder the user owns or manages). An agent can distinguish this from getFolder/updateFolder/shareFolder 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?

Gives concrete context for when each placement applies and permission gates for the top-level case, and it tells the agent the natural next step (file reports via updateReport's folderId or createReport). It lacks an explicit 'check listFolders/getFolder first' exclusion, but the duplicate-creation warning effectively signals that intent.

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