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

With no annotations, the description fully carries the burden and does so well: it discloses recoverability (messages go to Trash, nothing erased permanently), a permission prerequisite (owner must enable agent move/delete), and a batch cap (50 per call). These are exactly the behavioral facts an agent needs before invoking a destructive-looking operation.

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 action and its recoverability, then constraints. Every sentence earns its place, though the permission sentence is dense enough to slightly slow reading.

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 action, side effects, recovery path, permission gate, and batch limit. Nothing an agent needs to call it correctly is missing.

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 100%, so the schema already documents uids, folder, and mailbox. The description reinforces the uid provenance and the 50-item cap but adds no format or syntax detail beyond what the schema states, 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?

States a specific verb (Delete) and resource (messages), identifies the uid source (mail_search), and clarifies that this is a soft-delete to Trash. An agent can distinguish this from mail_move without inspecting either 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 explicit when-not conditions: only in a mailbox whose owner enabled the agent delete setting, only what the owner asked for, and never triggered by a received email's content. Strong safety routing, though it never names the sibling alternative (mail_move) for non-destructive relocation.

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