missive_list_conversation_draftsList draft messages on a conversation. Missive: GET /conversations/{id}/drafts.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The resource id (a UUID-like string). | |
| limit | No | Max records to return. | |
| until | No | Unix timestamp cursor — return records older than this (offset-less pagination). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description 'List draft messages' aligns with the readOnlyHint annotation, indicating a safe read operation. However, it adds no behavioral details beyond what annotations provide (e.g., pagination behavior of limit/until parameters could be explained but schema already covers them).
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 a single sentence plus the HTTP endpoint, front-loading the core action. It is efficient and easy to scan, though slightly more structured details could be added without bloat.
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 simple list tool with 3 parameters, no output schema, and readOnlyHint annotation, the description is minimally adequate. It covers the basic function but lacks usage guidance and behavioral elaboration, leaving some gaps for an AI agent to infer.
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 100%, so each parameter (id, limit, until) already has a description. The tool description does not add extra meaning, such as clarifying that 'until' is for cursor-based pagination. Baseline 3 is appropriate.
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 it lists draft messages on a conversation, distinguishing it from siblings like missive_create_draft (create) and missive_list_conversation_messages (list messages, not drafts). The verb 'List' and resource 'draft messages on a conversation' are specific.
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?
No guidance on when to use this tool versus alternatives such as missive_create_draft or missive_list_conversation_messages. The description lacks context about prerequisites (e.g., conversation must exist) or scenarios where drafts are relevant.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Every tool targets a unique resource-action combination (e.g., missive_get_contact vs missive_list_contacts). There is no overlap in functionality; the purposes are clearly distinct.
All tool names follow a strict 'missive_verb_noun' pattern in lowercase snake_case. Verbs are limited to create, get, list, and update, applied consistently across resources.
With 19 tools, the server is slightly above the ideal range (3-15) but still reasonable for covering multiple resources like contacts, conversations, messages, and lists. Each tool serves a specific purpose without unnecessary redundancy.
Core workflows are covered: listing, getting, creating contacts/drafts, managing conversations, and viewing sub-items. Minor gaps exist (no update for contacts, no delete for any resource), but these are acceptable for an initial release.