Skip to main content
Glama
Sign In

Post Stats

by app.openkrill
OverviewDiscussionsAdmin

Compare posts by views

compare_posts
Read-onlyIdempotent

Read 2 to 10 public posts (YouTube and TikTok can be mixed) and rank them by views, with likes per 1,000 views for each. Every row has the same fields as get_post_stats; a post that could not be read stays in the list with its error, ranked last.

Input Schema

NameRequiredDescriptionDefault
urlsYes2 to 10 post addresses. Address of one public post: a YouTube video or Short (youtube.com/watch?v=<id>, youtube.com/shorts/<id>, youtu.be/<id>, or the bare 11-character video id) or a TikTok video (tiktok.com/@user/video/<id>, tiktok.com/video/<id>, or a vm.tiktok.com or vt.tiktok.com short link). Platforms can be mixed.

Output Schema

NameRequiredDescriptionDefault
topNo
as_ofYesISO 8601 time the data was published by its source or fetched from it. A cached answer keeps the time of its fetch.
notesNo
postsYes
sourceYesWho the data comes from, to cite and to check it against.
ranked_byYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / urls / description
      Previous value: -"2 to 10 post addresses. Address of one public post: a YouTube video or Short (youtube.com/watch?v=<id>, youtube.com/shorts/<id>, youtu.be/<id>, or the bare 11-character video id) or a TikTok video (tiktok.com/@user/video/<id>). Platforms can be mixed."New value: +"2 to 10 post addresses. Address of one public post: a YouTube video or Short (youtube.com/watch?v=<id>, youtube.com/shorts/<id>, youtu.be/<id>, or the bare 11-character video id) or a TikTok video (tiktok.com/@user/video/<id>, tiktok.com/video/<id>, or a vm.tiktok.com or vt.tiktok.com short link). Platforms can be mixed."
  2. Changed1 schema field changed
    • changedInput schema / properties / urls / description
      Previous value: -"2 to 10 post addresses. Full address of one public post: a YouTube video or Short, or a TikTok video. Platforms can be mixed."New value: +"2 to 10 post addresses. Address of one public post: a YouTube video or Short (youtube.com/watch?v=<id>, youtube.com/shorts/<id>, youtu.be/<id>, or the bare 11-character video id) or a TikTok video (tiktok.com/@user/video/<id>). Platforms can be mixed."
  3. Changed2 schema fields changed
    • changedInput schema / properties / urls / description
      Previous value: -"2 to 10 post addresses. Full address of one public post: a YouTube video or Short, a TikTok video, or an X post. Platforms can be mixed."New value: +"2 to 10 post addresses. Full address of one public post: a YouTube video or Short, or a TikTok video. Platforms can be mixed."
    • changedOutput schema / properties / posts / items / properties / platform / enum
      Previous value: -[
-  "youtube",
-  "tiktok",
-  "x"
-]New value: +[
+  "youtube",
+  "tiktok"
+]
  4. Changed3 schema fields changed
    • addedOutput schema / properties / as_of
      Added value: +{
+  "description": "ISO 8601 time the data was published by its source or fetched from it. A cached answer keeps the time of its fetch.",
+  "type": "string"
+}
    • addedOutput schema / properties / source
      Added value: +{
+  "description": "Who the data comes from, to cite and to check it against.",
+  "properties": {
+    "name": {
+      "type": "string"
+    },
+    "url": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "name",
+    "url"
+  ],
+  "type": "object"
+}
    • changedOutput schema / required
      Previous value: -[
-  "ranked_by",
-  "posts"
-]New value: +[
+  "ranked_by",
+  "posts",
+  "as_of",
+  "source"
+]
  5. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's job is to add what they cannot. It does exactly that by disclosing failure semantics: an unreadable post stays in the list with its error and is ranked last, which an agent could not infer from the schema. Auth/rate-limit behavior is not mentioned, and 'public posts' only implicitly suggests no credentials are needed.

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?

Two sentences, zero filler: the first front-loads the operation and ranking metric, the second handles row shape and the error case. Nothing is repeated and no sentence could be dropped without losing information.

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 single-parameter read tool with an output schema and full annotation coverage, the description supplies everything an agent needs: input bounds, mixed-platform support, ranking criterion, and degraded-result handling. Return payload detail is correctly left to the output schema.

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 description coverage is 100% and the urls parameter already enumerates every accepted address form, so the description's '2 to 10' and mixed-platform note largely restate the schema's minItems/maxItems and item description. It adds no format or ordering guidance beyond the structured field, so the baseline of 3 applies.

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 ('read ... and rank them by views') plus the resource (public YouTube/TikTok posts) and the exact output shape (rank order, likes per 1,000 views). The multi-post comparison framing plus 'same fields as get_post_stats' makes it distinguishable from the single-post sibling at a glance.

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?

The 2-to-10 range and 'platforms can be mixed' give clear conditions for use, and the reference to get_post_stats implies this is the multi-post alternative to that single-post tool. It never explicitly says 'use get_post_stats for one post', so the routing is inferred rather than stated.

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

All Post Stats 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