category_videosVideos in a category.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| slug | Yes | ||
| per_page | No |
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | Array of category videos | |
| page | No | Current page | |
| total | No | Total videos in category | |
| paging | No | Pagination links | |
| per_page | No | Items per page |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "slug": "animation"
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "data": {
+ "description": "Array of category videos",
+ "items": {
+ "properties": {
+ "created_time": {
+ "description": "Creation timestamp",
+ "type": "string"
+ },
+ "description": {
+ "description": "Video description",
+ "type": "string"
+ },
+ "duration": {
+ "description": "Duration in seconds",
+ "type": "number"
+ },
+ "name": {
+ "description": "Video title",
+ "type": "string"
+ },
+ "pictures": {
+ "description": "Picture/thumbnail data",
+ "type": "object"
+ },
+ "uri": {
+ "description": "Video URI",
+ "type": "string"
+ },
+ "user": {
+ "description": "Uploader user object",
+ "type": "object"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "page": {
+ "description": "Current page",
+ "type": "number"
+ },
+ "paging": {
+ "description": "Pagination links",
+ "type": "object"
+ },
+ "per_page": {
+ "description": "Items per page",
+ "type": "number"
+ },
+ "total": {
+ "description": "Total videos in category",
+ "type": "number"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey readOnly, openWorld, idempotent, and non-destructive hints. The description adds no behavioral context beyond the name, missing details on pagination, error handling, or what happens with invalid slugs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single phrase, which is too brief to be useful. It is under-specified rather than concise, missing opportunities to add value in few words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 parameters, an output schema, and siblings, the description is insufficient. It does not cover pagination, filtering, or return format, leaving the agent without enough context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 3 parameters (slug, page, per_page) with 0% description coverage. The description does not explain any parameter, even though slug is required. The agent must infer semantics from property names only.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Videos in a category.' indicates the tool returns videos for a given category. However, it is vague and does not differentiate from sibling tools like 'category', 'channel_videos', or 'videos_search' that also return videos.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool over alternatives, nor any exclusions or prerequisites. The agent receives no context for decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools have overlapping purposes: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-duplicates, and the polymarket_* family has six tools with blurred boundaries. The Vimeo tools are distinct, but the massive unrelated Pipeworx set creates ambiguity about which tool is appropriate for a given task.
Tool names mix conventions: Vimeo tools use bare nouns (video, channel, user), while Pipeworx tools use verb_noun (resolve_entity, validate_claim) or noun_verb (ai_visibility_check). Some names like ask_pipeworx and pipeworx_feedback do not follow a consistent verb-first pattern.
40 tools is far too many for a Vimeo server; only 9 tools are Vimeo-related, and the remaining 31 are an unrelated Pipeworx data toolkit. This inflates the surface area and makes the set unwieldy.
The Vimeo surface covers read operations (search, get, list) but lacks any write operations like upload, update, or delete videos. It also misses common Vimeo features like comments, likes, or portfolio management, so common tasks would hit dead ends.