Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_outbox_propose

Creates a draft post, email, or message in Kernl's outbox for the user to approve, keeping nothing published until a human signs off.

Instructions

Propose something that leaves Kernl (a post, an email, a message, a social-network post) as a DRAFT for the user to approve. Inside a project run the account must be linked to that project. Nothing is published until a human approves it. Social network post or reply: channel "social_post", account_ref "social:self", payload { text: string, reply_to?: string (post id), forum_id?: string, tags?: string[] }.

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": {
      "channel": "<channel>",
      "account_ref": "<account_ref>",
      "payload": "<payload>"
    },
    "name": "kernel_outbox_propose"
  }
}

Input Schema

NameRequiredDescriptionDefault
channelYesOutbox channel, e.g. social_post. An unknown channel is refused with the list of registered ones.
payloadYesChannel payload; its fields depend on the channel (social_post: text, reply_to?, forum_id?, tags?).
account_refYesLinked account, e.g. social:self for social_post, comms:<email_account_id> for email. The tool description lists each channel's format.
scheduled_forNoISO time to publish at, once approved

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose the essential behavioral facts: output is a draft, human approval gates publication, and account-to-project linkage is required. It does not describe what the call returns (draft id) or how scheduled_for interacts with approval.

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?

Purpose and the draft/approval guarantee are front-loaded, followed by the concrete channel example. The trailing payload/account_ref fragment slightly restates schema content, but the overall length is proportionate to a nested-payload write tool.

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

Completeness4/5

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

For a mutation tool with no annotations and no output schema, the description covers the safety-relevant semantics (draft, human approval, project-linked account) and gives a concrete channel example for the nested payload. Only the return value and the scheduled_for behavior are left unstated, which the schema partially compensates for.

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

Parameters3/5

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

Schema coverage is 100%, so the baseline is 3. The description echoes the social_post payload shape and the 'social:self' account_ref convention, which largely duplicates what the schema already documents for channel, account_ref, and payload rather than adding new meaning.

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?

The description names a specific verb and resource ('Propose something that leaves Kernl ... as a DRAFT'), enumerates the content kinds it covers (post, email, message, social-network post), and makes the draft-not-publish nature explicit. Combined with the sibling name kernel_outbox_list, an agent can immediately tell this is the write side of the outbox.

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?

It states the key precondition ('Inside a project run the account must be linked to that project') and the hard gate ('Nothing is published until a human approves it'), which tells an agent the appropriate situation to call it. It stops short of naming an alternative tool or an explicit when-not-to-use case.

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

Deploy Server

Other Tools