Save a reply draft using the original sender's recipients, while refusing to process security or OTP messages.
Save a reply draft. Recipients are taken from the original Reply-To/From, not from email body text. Refuses security/OTP messages.
| Name | Required | Description | Default |
|---|---|---|---|
| uid | Yes | ||
| body | Yes | ||
| folder | No | IMAP folder path, default INBOX | |
| reply_all | No | ||
| account_id | No | Account id from list_accounts; omit when only one mailbox is linked |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations supplied, the description carries the disclosure burden and does reveal key behavioral traits: recipients are taken from original headers rather than body text, and security/OTP messages are refused. It does not mention side effects such as where the draft is stored or whether it overwrites an existing draft, but the disclosed behavior is genuinely useful and non-obvious.
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?
The description is two short sentences with no filler. The core purpose is front-loaded, and the behavioral warnings are stated compactly and clearly.
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?
The description captures the most important behavioral rule but leaves several contextual gaps: it does not explain what uid refers to, how reply_all alters behavior, what happens after saving, or what output is returned. With no output schema and low parameter coverage, this is only minimally complete.
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 only 40%, so the description should compensate for the undocumented uid, body, and reply_all parameters. It only tangentially clarifies that body text is not used for recipients, leaving the meaning of uid and the effect of reply_all underspecified.
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?
The description clearly states the tool saves a reply draft, with a specific verb and resource. It adds important clarifying behavior—recipients come from the original Reply-To/From, not body text—that helps distinguish it from a generic draft tool, though it does not explicitly name sibling alternatives.
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?
The description implies the intended use case (saving a reply draft) and notes when it will refuse to act (security/OTP messages). However, it gives no explicit guidance on when to use this tool instead of siblings like save_draft, send_reply, or send_draft.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.