Graunt

Search the Graunt catalog

search

Read-only

Search the Graunt catalog of evaluated data packets. Returns matching packets with their id, title, and public URL. Start here to find data, then read one with fetch.

Input Schema

Name	Required	Description
`kind`	No	Only listings of this kind. video: video listings.
`limit`	No	Max results; default 20, cap 50.
`query`	Yes	Search keywords.
`camera_view`	No	Only video listings shot from this camera view.
`ai_generation`	No	Keep only packets whose seller declares this AI-generation extent: NONE (not AI-generated), PARTIAL or FULL. A seller declaration, not a Graunt finding. AI processing of real material (cleaning, labeling, transcribing, captioning, structuring) is not AI generation, and a packet that contains video declares NONE.
`video_subject`	No	Only video listings whose footage shows this subject.

Output Schema

Name	Required	Description	Default
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 30, 2026

changedInput schema / properties / ai_generation / description

Previous value: -"Keep only packets whose seller declares this AI-generation extent: NONE (not AI-generated), PARTIAL or FULL. A seller declaration, not a Graunt finding."New value: +"Keep only packets whose seller declares this AI-generation extent: NONE (not AI-generated), PARTIAL or FULL. A seller declaration, not a Graunt finding. AI processing of real material (cleaning, labeling, transcribing, captioning, structuring) is not AI generation, and a packet that contains video declares NONE."

Changed4 schema fields changedOct 29, 2026

addedInput schema / properties / ai_generation

Added value: +{
+  "description": "Keep only packets whose seller declares this AI-generation extent: NONE (not AI-generated), PARTIAL or FULL. A seller declaration, not a Graunt finding.",
+  "enum": [
+    "NONE",
+    "PARTIAL",
+    "FULL"
+  ],
+  "type": "string"
+}

addedInput schema / properties / camera_view

Added value: +{
+  "description": "Only video listings shot from this camera view.",
+  "enum": [
+    "FIRST_PERSON",
+    "AERIAL_OR_DRONE",
+    "VEHICLE_OR_DASHCAM",
+    "FIXED_CAMERA",
+    "OTHER"
+  ],
+  "type": "string"
+}

addedInput schema / properties / kind

Added value: +{
+  "description": "Only listings of this kind. video: video listings.",
+  "enum": [
+    "video"
+  ],
+  "type": "string"
+}

addedInput schema / properties / video_subject

Added value: +{
+  "description": "Only video listings whose footage shows this subject.",
+  "enum": [
+    "PEOPLE_TALKING",
+    "PEOPLE_IN_ACTION",
+    "PEOPLE_HANDLING_OBJECTS",
+    "HOW_TO_AND_TASKS",
+    "SPORTS_AND_FITNESS",
+    "MUSIC_AND_PERFORMANCE",
+    "ANIMALS",
+    "NATURE",
+    "CITIES_AND_BUILDINGS",
+    "DRIVING_AND_TRANSPORTATION",
+    "INDUSTRY_AND_WORK_SITES",
+    "FOOD_AND_COOKING",
+    "PRODUCTS_AND_RETAIL",
+    "ANIMATION",
+    "VIDEO_GAMES"
+  ],
+  "type": "string"
+}

First observedSep 6, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already state readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the catalog scope and result fields (id, title, public URL), but it does not disclose ranking behavior, pagination constraints, authentication needs, or rate limits beyond what the annotations and schema provide.

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?

The description is three concise sentences with no wasted wording. It front-loads what the tool searches, then states what it returns, then gives the follow-up workflow.

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?

Given the full schema, rich annotations, and an output schema, the description is largely complete for invocation: it states scope, return fields, and the follow-up fetch step. The main remaining contextual gap is that it does not clarify how this search differs from the sibling search_assets.

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 schema fully documents all six parameters, including four enumerated filters and limit defaults. The description adds no parameter-specific meaning beyond the schema, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: search the Graunt catalog of evaluated data packets, and it names the return fields. It also contrasts with fetch as the next step, but it does not distinguish this tool from the sibling search_assets, leaving a possible ambiguity for similarly named search tools.

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?

It gives clear usage guidance: "Start here to find data, then read one with fetch." That explicitly covers when to use this tool and which alternative to use afterward. It does not explain when to use it instead of search_assets or match_video_spec, so it lacks exclusions or sibling routing.

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

All Graunt 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?