Draft and send an email on behalf of the user via their connected Gmail or Outlook account. The tool creates the draft first, then sends it.
Send an email on behalf of the user via their connected email account (Gmail or Outlook). Creates a draft first, then sends it.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | Recipient email address | |
| body | Yes | Email body text | |
| subject | Yes | Email subject line |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It does disclose one genuinely useful trait — the draft-then-send sequence, which implies a two-step operation and possible draft artifacts — but omits whether sending is irreversible, what permissions or confirmation are required, and how failures are surfaced.
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?
Two short sentences, purpose front-loaded, with the operational detail in the second sentence. No filler or repetition.
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 3-required-param mutation tool with no annotations and no output schema, the description covers the what and a bit of the how but leaves gaps: no return value, no error behavior, no auth prerequisite, and no statement about irreversibility. Adequate but not 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 coverage is 100%, so to/subject/body are already documented in the schema. The description adds no format details beyond that (e.g., plain text vs HTML body, multiple recipients), so the baseline of 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 and resource (send an email), names the delivery channel (user's connected Gmail or Outlook account), and describes the mechanism (draft first, then send). It is unmistakably distinct from read_inbox, the only sibling touching the same resource.
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?
There is no when-to-use guidance, no prerequisites (e.g., that an email account must already be connected), and no exclusions. The agent is left to infer that this is the only write path for email, with no mention of alternatives or conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.