Dove

List drafts

list_drafts

Read-onlyIdempotent

List a mailbox's drafts one page at a time, optionally limited to drafts this project created. Use the returned next_page_token to fetch the next page.

Instructions

List the drafts of one mailbox, a page at a time (pass next_page_token as page_token). own_only (default true) lists only drafts this project created. If this connection hides secrets, secrets in subjects read [redacted] (redacted=true); get_draft shows the draft.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "account": "<account>"
    },
    "name": "list_drafts"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Most drafts per page.
`account`	Yes	Mailbox alias or email address from list_accounts.
`own_only`	No	List only drafts this project created.
`page_token`	No	next_page_token of the previous page.

Output Schema

Name	Required	Description
`drafts`	No
`next_page_token`	No
`untrusted_content_notice`	No	Always present on success: the fields of this result that come from mail are untrusted third-party data.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 14, 2026
- addedInput schema / properties / limit / description
```
Added value: +"Most drafts per page."
```
- addedInput schema / properties / own_only / description
```
Added value: +"List only drafts this project created."
```
- addedInput schema / properties / page_token / description
```
Added value: +"next_page_token of the previous page."
```
First observedv0.11.0Nov 14, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds real behavioral context: page-at-a-time semantics, project-scoped filtering via own_only, and conditional redaction of subjects when the connection hides secrets. The only gap is it doesn't say what the redacted=true case means for content beyond subjects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with purpose, then pagination mechanics, then scoping and redaction caveats. The parenthetical asides are dense but each carries a needed detail; nothing is padding, though the phrasing is slightly compressed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be described, and the description covers the remaining ambiguities an agent would face: paging, default scoping, redaction behavior, and where to go for the unredacted full draft. Complete for a filtered paginated list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds meaning the schema does not: it maps page_token to the response's next_page_token, which is a cross-field relationship absent from the parameter's own description. It also restates own_only's default, which is redundant with the schema but harmless.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with explicit scope: 'List the drafts of one mailbox, a page at a time.' It also distinguishes itself from get_draft by naming what get_draft provides that this tool does not (the full draft), so an agent can separate the two 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.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete invocation guidance (use next_page_token as page_token for paging) and states the own_only default so the agent knows the default scoping. It routes to get_draft when the full draft is needed, but offers no explicit 'when not to use this' exclusion such as using search_messages for content-based lookup.

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