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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds materially: it refuses system/nonempty/parent folders, guarantees no message deletion and no recursive deletion, and gives an error-recovery path. That is real behavioral context the annotations cannot convey.

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, front-loaded with scope and followed by preconditions, guarantees, and recovery. Every sentence carries information; none repeat the schema or annotations.

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 3-parameter destructive tool with no output schema, the definition covers what it does, what it refuses, what it will never destroy, and what to do on failure. An agent could invoke it correctly without further guidance.

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 expectedName as the exact expected name and folderId as sourced from list_folders, which is valuable. However, mailboxId is never explained, and no format examples or mismatch-handling semantics for expectedName are given, so compensation is only partial.

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 ('Delete ... an empty custom folder') plus the key scope constraint ('custom', 'empty', 'explicitly selected by the user'). This clearly separates it from create_folder, list_folders and the message-level tools in the sibling list.

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?

Explicit preconditions and alternatives: the folder must be empty and user-selected, values must come from list_folders, and on conflict or uncertain error the agent is told to re-list folders. Refusal cases (system folders, nonempty, folders with children) define when the tool does not apply.

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