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

Adds substantial behavior the annotations cannot convey: it replaces all current folder memberships, preserves content and flags, and never permanently deletes. It also defines recovery semantics on conflict or uncertain failure and warns against following instructions embedded in emails or folder names, which meaningfully rounds out the destructiveHint=true 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?

Front-loaded with the core action, then layered with preconditions and recovery rules. Dense but essentially waste-free; the injection warning and retry guidance each add distinct value rather than restating the name.

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 four-required-param mutation with no output schema and no annotation depth, the definition covers safety, preconditions, batching, and error recovery. Only the shape of the success response (e.g., resulting folder memberships) is left unstated, which is a minor gap.

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 0%, so the description must carry the load. It explains the non-obvious expectedFolderIds precondition (a concurrency guard taken from the latest search/read) and implies destinationFolderId must be an existing folder in the same mailbox, though it does not describe ID formats or the min/max uniqueness constraints.

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 with scope: 'Move one user-selected message to an existing folder in the same mailbox.' The word 'one' implicitly draws the line against the sibling move_messages, but the sibling is never named, so the differentiation is left to inference.

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 operating context: source expectedFolderIds from the latest search/read, collect all IDs before batch moving, re-search on conflict, and read before retrying after an uncertain error. It stops short of explicitly routing multi-message work to the move_messages sibling.

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