Skip to main content
Glama
Sign In

Spaces

by com.spacesos.api
OverviewDiscussionsAdmin

Get a post's photos and videos

get_post_media
Read-onlyIdempotent

Every photo and video of a post, reel or carousel, with a thumbnail and a short-lived link. Pass download with the item number (0 is the first) to get that file as base64 (at most 8 MB). Counts as browsing.

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": {
      "account_id": "<account_id>",
      "post_id": "<post_id>"
    },
    "name": "get_post_media"
  }
}

Input Schema

NameRequiredDescriptionDefault
post_idYesThe post id (social_id from list_own_posts or list_user_posts).
downloadNoOptional: the item to download (0-19).
account_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds genuinely new behavior: links are short-lived (expiry), downloads are base64-capped at 8 MB, and the call is metered as browsing — all facts absent from annotations and schema. It stops short of saying what happens when the 8 MB cap is exceeded.

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?

Two sentences, front-loaded with the resource and return shape, then the optional download mode and the quota note. No filler; would reach 5 only by organizing the download caveats a bit more distinctly.

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 3-parameter read tool with no output schema, the description covers what is returned, the alternative download mode and its limits, and the cost model. Remaining gaps (behavior past 19 items, failure when media is unavailable) are minor.

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 only 67% — account_id has no description at all — so some compensation is required. The description does explain the download parameter's semantics (0 is the first item, returns base64, 8 MB cap), which goes beyond the schema's terse "the item to download (0-19)", but it says nothing about account_id, leaving one gap.

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?

"Every photo and video of a post, reel or carousel" names the resource precisely and scopes it beyond just posts, which distinguishes it from get_post (which presumably returns post-level metadata). The return shape (thumbnail + short-lived link) is stated up front.

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

Usage Guidelines3/5

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

Usage is only implied: "Counts as browsing" hints that calling this consumes a browsing quota, and the download parameter implies a second, heavier mode. No explicit when-to-use/when-not-to-use guidance or named alternative (e.g. get_post, get_messaging_attachment) is given, so the agent must infer positioning.

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

All Spaces toolsInspect
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