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

Annotations already flag destructiveHint=true and openWorldHint=false, so the description's added value is explaining precisely what is destroyed (the emptied duplicate folders) versus what is preserved (the messages, consolidated into the kept folder). That is real behavioral context beyond the annotation. It still omits partial-failure behavior and required mailbox permissions.

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?

Two sentences with no waste; the mutation is front-loaded and the confirmation requirement follows it. Every clause earns its place.

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 destructive, no-output-schema tool, the description covers the core flow and the safety gate. Remaining gaps (whether messages keep their labels, partial-failure handling, and permission requirements) are modest given the annotations already carry the destructive signal.

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%, and each parameter is already documented in the schema, including that folderIds must contain the kept folder and that keepFolderId survives. The description's 'set of duplicate folders into one folder to keep' merely restates that mapping, adding no format or constraint detail, so the baseline 3 applies.

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 description names a specific verb chain and resource: move messages from duplicate folders into a kept folder, then delete the emptied folders. It is clearly distinguishable from find_duplicate_mail_folders, delete_mail_folder, and move_messages by its merge-and-cleanup scope, but it never names those siblings explicitly.

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?

The only usage instruction is the procedural 'ask the user to confirm before calling this,' which is useful but addresses confirmation rather than when-to-use. It implies the tool follows duplicate discovery, but it never states prerequisites or when to prefer this over delete_mail_folder or move_messages.

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