prepare_send

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

Annotations declare openWorldHint and destructiveHint=false, but the description adds genuinely new operational facts: nothing is sent, the From field is locked to the account email, and the issued token expires in 10 minutes. That expiry and the From-locking constraint are not derivable from the structured fields and are useful for correct invocation.

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 fact ('Create a local preview; sends nothing') and each following sentence carries a distinct constraint. It is a bit dense and could be trimmed, but no sentence is pure 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 six-parameter, zero-coverage mutation-adjacent tool with no output schema, the description leaves gaps: it hints a token is produced but never says so explicitly or how it feeds send_prepared, and several parameters go unexplained. It covers the reply path well but is incomplete for the tool as a whole.

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?

With 0% schema coverage the description must carry full parameter load, and it only partially does. It explains account_id (From is locked to its email), reply_to_message_id (the parent provider message_id), and subject (must match for replies), but says nothing about recipients, body, or the mailbox parameter.

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 — 'Create a local preview' — and immediately clarifies 'sends nothing', which distinguishes it from the sibling send_prepared that actually dispatches. An agent can tell the two apart without opening 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 clear workflow context ('Show the entire preview to the user before sending') and a conditional rule for replies (provide the parent provider message_id, subject must match). It never names send_prepared as the follow-up step, so the routing to the actual send tool is left implicit.

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