Postfjord

AI compose (server side)

postfjord_ai_compose

Asks Postfjord's built-in composer to draft text per channel from a brief, in the brand voice, and returns the text only: nothing is saved (save it with postfjord_create_draft). To save a draft for every channel and an email from one idea in one call, use postfjord_repurpose_idea instead. Uses the workspace AI budget. Usually you can write the post yourself instead; use this when the user explicitly wants Postfjord's composer.

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": {
      "brief": "<brief>",
      "channels": "<channels>"
    },
    "name": "postfjord_ai_compose"
  }
}

Input Schema

Name	Required	Description
`tone`	No	A tone for this post only, such as playful or calm. Left out: the brand voice.
`brief`	Yes	What the post is about, in a sentence or a few.
`channels`	Yes
`mediaSummary`	No	What the pictures or video show, so the text can talk about them.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 28, 2026
- addedInput schema / properties / brief / description
```
Added value: +"What the post is about, in a sentence or a few."
```
- addedInput schema / properties / brief / maxLength
```
Added value: +4000
```
- addedInput schema / properties / brief / minLength
```
Added value: +1
```
- addedInput schema / properties / mediaSummary / description
```
Added value: +"What the pictures or video show, so the text can talk about them."
```
- addedInput schema / properties / mediaSummary / maxLength
```
Added value: +1000
```
- addedInput schema / properties / tone / description
```
Added value: +"A tone for this post only, such as playful or calm. Left out: the brand voice."
```
- addedInput schema / properties / tone / maxLength
```
Added value: +200
```
First observedOct 26, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing three things they cannot convey: the call consumes the workspace AI budget (a cost/rate consideration), nothing is persisted (so no cleanup or dedupe worry), and the response is bare text with no draft object. The 'nothing is saved' wording is consistent with readOnlyHint=false, which reflects budget consumption rather than persistence.

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

Conciseness5/5

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

Three tight sentences, front-loaded with what it does and the non-persistence fact, then alternatives, then the gating preference. Every clause carries information an agent needs; nothing is padding.

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?

Compensates for the absent output schema by stating the return is text only, and pairs that with cost and persistence caveats. For a 4-parameter, 2-required generation tool, an agent has everything needed to decide whether to call it and what it will get back.

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 75% and the description reinforces the two meaningful parameters — the brief drives the content and output is generated per channel entry — while implying tone defaults to brand voice. It adds modest routing meaning over the schema but leaves the channel object's id/platform structure and mediaSummary to the schema.

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 (built-in composer drafts text per channel from a brief, in brand voice) plus the exact output contract: text only, nothing saved. It explicitly differentiates itself from postfjord_create_draft and postfjord_repurpose_idea, so an agent can place it among 60+ siblings without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Gives both routing alternatives and the selection condition: use postfjord_repurpose_idea for one idea across every channel plus an email, save with postfjord_create_draft, and only call this when the user explicitly wants Postfjord's composer rather than self-written text. This is explicit when-to-use, when-not-to-use, and which sibling to pick instead.

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

All Postfjord tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?