Skip to main content
Glama

kelpo_view_take

Read-onlyIdempotent

Contact sheet of a finished video or shot take: ONE image with frames still frames in time order (left to right, top to bottom; times gives each frame's second). MCP returns it as a native image: look at it yourself to judge the take (hands and fingers, extra limbs, faces, objects appearing or vanishing, product fidelity, setting) and tell the user plainly. Kelpo does not judge the pictures of a take for you. To redo a shot: kelpo_retake_shoot then kelpo_answer_offer after the user's explicit yes on the price. Arguments: {"path": {"id": ""}, "query": {"frames": 12}}

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": {
      "path": "<path>"
    },
    "name": "kelpo_view_take"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
queryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety bar is low; the description still adds real value by disclosing the return medium (a native image the agent must inspect itself) and the division of labor ('Kelpo does not judge the pictures of a take for you'). It also flags the consent requirement before a paid retake, though it does not describe image resolution or how `times` is delivered.

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 the core fact (one image, frames in order), followed by the agent's duty, then the redo path and an argument example — a sensible priority order. Slight redundancy between 'look at it yourself to judge the take' and 'Kelpo does not judge the pictures', and mid-sentence line breaks hurt scannability.

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?

With no output schema, the description correctly carries the return contract: one contact sheet image, frames ordered left-to-right/top-to-bottom, `times` giving each frame's second. Nested `path.id` is clarified only via the example, which is adequate but a touch implicit for a required parameter.

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 description coverage is 0% for the top-level nested objects, and the description compensates by spelling out that `frames` is the count of evenly spaced stills, that `path.id` is a job id, and by showing a literal argument example with frames: 12. It stops short of explaining the 4–12 bounds or the default of 8, which the schema carries silently.

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+resource: produces a contact sheet (one image) of a finished video/shot take with `frames` stills in reading order. It is immediately distinguishable from siblings like kelpo_video_download or kelpo_get_shoot because the output is explicitly a single native image meant for visual inspection.

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?

Tells the agent exactly what to do with the result (judge hands, limbs, faces, object continuity, product fidelity and report plainly) and routes the redo workflow to kelpo_retake_shoot then kelpo_answer_offer after an explicit user yes on price. It does not explicitly say when to prefer this over viewing the full video or a single still, so it falls just short of full alternative coverage.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources