Preflight

Posts

list_posts

Read-only

Posts, most recent first by when they went out (still-to-come posts are always included). Filter by status, channel, network, tag, a from/to window, or failedOnly for posts with a channel that failed. Each channel's status, link, error, errorCode and whether it is permanent. Page with cursor: pass back nextCursor until it is absent — a page can hold fewer than limit after filtering. get_post gives one post in full.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_posts"
  }
}

Input Schema

Name	Required	Description
`to`	No	ISO time, the end of the window.
`tag`	No	Only posts with this tag, by name, such as a campaign.
`days`	No	Without from/to: how far back published posts go, at most 730. Posts still to come are always included. Defaults to 30.
`from`	No	ISO time. With to, only posts that went out (or are due) in [from, to).
`limit`	No	Posts read per page, at most 100. Defaults to 20.
`cursor`	No	nextCursor from the previous page.
`status`	No	Only posts in this state. Omit for all of them.
`network`	No	Only posts going to this network.
`channelId`	No	Only posts going to this channel, from list_channels.
`failedOnly`	No	Only posts with at least one channel that failed.

Output Schema

Name	Required	Description	Default
`posts`	Yes
`nextCursor`	No	Pass as cursor for the next page. Absent on the last page.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

changedInput schema / properties / network / enum

Previous value: -[
-  "youtube",
-  "tiktok",
-  "facebook",
-  "instagram",
-  "threads",
-  "twitter",
-  "linkedin",
-  "pinterest",
-  "bluesky",
-  "mastodon",
-  "telegram",
-  "discord",
-  "tumblr"
-]New value: +[
+  "youtube",
+  "tiktok",
+  "facebook",
+  "instagram",
+  "threads",
+  "linkedin",
+  "pinterest",
+  "bluesky",
+  "mastodon",
+  "telegram",
+  "discord",
+  "tumblr"
+]

Changed2 schema fields changedOct 29, 2026

addedInput schema / properties / tag

Added value: +{
+  "description": "Only posts with this tag, by name, such as a campaign.",
+  "type": "string"
+}

addedOutput schema / properties / posts / items / properties / tags

Added value: +{
+  "items": {
+    "properties": {
+      "color": {
+        "type": "string"
+      },
+      "id": {
+        "type": "string"
+      },
+      "name": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

First observedOct 14, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly/non-destructive/closed-world, and the description adds real behavioral context beyond them: result ordering, the fact that upcoming posts bypass the date window, and the caveat that a page may hold fewer than limit after filtering. Return-shape detail is partly redundant given the output schema, which keeps it from a 5.

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-loaded with identity, ordering, filters, then paging — a sensible order for an agent reading top-down. The mid-sentence 'Each channel's status, link, error, errorCode and whether it is permanent' is the one portion that could be trimmed since the output schema already carries return fields.

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?

For a 10-parameter, zero-required list tool with an output schema and full annotation coverage, the description supplies everything else an agent needs: ordering, default windowing behavior, cross-filter interplay, paging termination rule, short-page caveat, and a pointer to the single-record alternative.

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 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema does not: 'days' only applies when from/to are absent, caps at 730, defaults to 30, and still-to-come posts survive regardless. Pagination via nextCursor until absent is also spelled out as a loop, not just a field.

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?

Opens with a specific verb+resource ('Posts') plus ordering semantics (most recent first by publish time) and an explicit carve-out that still-to-come posts are always included. It also names the sibling it is not — 'get_post gives one post in full' — so an agent can separate list vs. single-fetch without opening either schema.

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?

Enumerates the practical selection levers (status, channel, network, tag, from/to window, failedOnly) and points to get_post for a full single record. It does not state explicit when-not conditions or contrast with other list siblings (e.g. list_comments), so it stops short of a 5.

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

All Preflight 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.