Upload a reply draft you wrote for a mission.
The mission moves to pending_approval and surfaces for the operator to
approve or edit. `reasoning` is optional, one-sentence justification for
the audit log.
| Name | Required | Description | Default |
|---|---|---|---|
| draft | Yes | The reply you wrote, exactly as it should be sent. | |
| reasoning | No | Optional one-sentence reason for the draft, kept in the audit log. | |
| mission_id | Yes | The mission's id, from get_missions. |
Changes observed during successful MCP inspections.
Input schema / properties / draft / descriptionAdded value: +"The reply you wrote, exactly as it should be sent."Input schema / properties / mission_id / descriptionAdded value: +"The mission's id, from get_missions."Input schema / properties / reasoning / descriptionAdded value: +"Optional one-sentence reason for the draft, kept in the audit log."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), but the description adds meaningful state-transition detail: the mission moves to pending_approval, surfaces for operator review, and reasoning is logged to the audit log. That is real behavioral context beyond the structured fields, though it doesn't reconcile what idempotent uploads mean.
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, front-loaded with the core action and followed by the consequence. Nothing redundant; the backticked parameter name gives a useful inline pointer.
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 three-parameter mutation tool with no output schema, the description covers the action, required inputs, and the resulting state change well. Minor gaps remain around error behavior and whether re-uploading replaces the prior draft (relevant given idempotentHint=true).
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 the schema already documents all three parameters. The description's note that `reasoning` is an optional one-sentence justification largely restates the schema's own 'kept in the audit log' text, adding little beyond the documented baseline.
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 (upload) and resource (a reply draft for a mission), and clarifies the downstream effect (mission moves to pending_approval). This distinguishes it from siblings like approve_mission, reject_mission, and draft_mission, which handle different stages of the same workflow.
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 usage ('a reply draft you wrote') and explains the downstream workflow, but never explicitly names alternatives or states when to prefer this over approve_mission/reject_mission or how it relates to draft_mission. The when-to-use is left to inference.
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.