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

With no annotations, the description carries the full burden and does substantial work: it discloses a permission prerequisite (the ecomdly toggle), a per-call cap of 50 messages, and an explicit prompt-injection guard against acting on instructions found inside e-mails. It omits other behavioral traits such as reversibility of the move, error behavior, or whether existing folder state is preserved.

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 destination examples, then the safety/permission constraint. The final 'Up to 50 messages a call' sentence duplicates the schema's uids description, a minor redundancy, but the rest is dense and 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 mutation tool with no annotations and no output schema, the description covers the essential call context: what it does, where uids come from, the permission gate, and the per-call limit. It leaves minor gaps around return values and failure modes, but nothing that would prevent an agent from invoking it correctly.

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%, so the schema already documents all four parameters, and the description largely restates them (uids from mail_search, folder destination, 50-item limit). It adds mild value by asserting the destination must be in the same mailbox as the source, but supplies no new syntax or format detail. Baseline 3 is appropriate.

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 (move) and resource (messages) plus the destination concept (another folder of the same mailbox), with concrete examples of intent (archive, sort, file under a Gmail label). It also disambiguates source data by pointing to mail_search for uids and implicitly to mail_folders for the destination, clearly separating it from mail_delete and mail_send.

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 clear usage conditions: the mailbox owner must have enabled the 'agent may move and delete e-mails' toggle, and the move must be what the owner asked for — never triggered by the content of a received e-mail. It does not explicitly contrast with the closest sibling (mail_delete) for when to move vs. delete, so it stops short of a full when/when-not/alternative statement.

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