Postfjord

Preview post pictures

postfjord_preview_post

Idempotent

Changes nothing on the post. The exact picture each channel of a post will send, as links valid for one hour: per channel its platform, format and shape (aspect), and per picture the link, width, height and mode (crop or whole; null for a video or document, which go as they are, and for a channel from before shapes). errors says what would stop a channel's pictures. Call it before postfjord_schedule_post or postfjord_publish_now and show the person each channel's picture (open the links, or show them as images). Look for crops that cut off people or words in the picture: for those, set fit mode "whole" or a focus with postfjord_update_post, then preview again. A picture not made yet is made now (a few seconds), which counts toward the workspace's preview limits and storage; with a read-only key nothing is made and errors names the picture instead.

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": {
      "postId": "<postId>"
    },
    "name": "postfjord_preview_post"
  }
}

Input Schema

Name	Required	Description	Default
`postId`	Yes	A post id, from postfjord_list_calendar or postfjord_create_draft.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 28, 2026
- addedInput schema / properties / postId / description
```
Added value: +"A post id, from postfjord_list_calendar or postfjord_create_draft."
```
First observedOct 26, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Adds substantial context beyond annotations: links expire in one hour, on-demand generation takes a few seconds and counts toward preview limits/storage (consistent with readOnlyHint=false), and a read-only key yields errors instead of generated pictures. It also explains the null mode case for video/document and legacy channels — genuinely useful behavioral disclosure.

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?

Front-loads the safety guarantee ('Changes nothing on the post') and every sentence carries real information about output shape, generation cost, or remediation. It is dense and slightly run-on but not padded.

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?

With no output schema, the description fully compensates by describing the return structure (per channel platform/format/shape; per picture link/width/height/mode; errors) and the generation cost/limits. An agent knows exactly what to expect and how to act on it.

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?

Only one parameter (postId) with 100% schema coverage and a schema description pointing to its sources (list_calendar, create_draft). The description adds no further param semantics, so the 3 baseline for fully-covered schemas applies; the rich per-channel/per-picture detail describes return shape, not the parameter.

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?

Names a specific action (preview) on a specific resource (each channel's picture for a post) and immediately scopes it with 'Changes nothing on the post.' It explicitly situates itself relative to siblings — used before postfjord_schedule_post/postfjord_publish_now, fixed via postfjord_update_post — so an agent can distinguish it from get_post or upload_media without opening schemas.

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 explicit when-to-use ('Call it before schedule_post or publish_now and show the person each channel's picture') and a remediation loop ('set fit mode whole or a focus with update_post, then preview again'). The read-only-key caveat further delineates the condition under which output differs.

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?