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

Adds real context beyond the destructiveHint annotation: it is RECOVERABLE, not a permanent delete, restorable via untrash_message, requires gmail.modify, and gives a reconnect hint for older accounts. This is meaningful behavioral disclosure. Slight deduction because it doesn't describe the response or what happens to labels/read-state.

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-loads the core action and the sibling distinction, then layers reversibility, prerequisites, and the confirmation step. Dense but every clause carries actionable information with no filler.

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 2-param mutation tool with no output schema, it covers scope, reversibility, restore path, auth scope, multi-account routing, and a safety confirmation. Nothing an agent needs to invoke 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 both parameters are already documented in the schema, including the multi-account condition for `account`. The description largely restates those meanings and adds no syntax or format details beyond what the schema provides, 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 precise verb+resource ("Move ONE Gmail MESSAGE to Trash") and explicitly distinguishes itself from the sibling organize_messages' thread-level `trash` action. An agent can immediately tell it apart from organize_messages, untrash_message, and delete-related tools.

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?

Names the alternative (organize_messages for whole threads) and the restore counterpart (untrash_message), states the multi-account condition for `account`, and even gives an operational instruction to confirm with the user first. When-to-use and when-to-use-something-else are both covered.

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