Blender Bridge

Panel: read latest screenshot

view_latest

Read-onlyIdempotent

App-only adapter that reads the panel's latest existing preview and view-state counters. since is the last preview sequence already displayed; scene_version and instance_id identify the panel's last known scene and runtime. Optional wait_ms waits up to 25 seconds for a change. Does not start a new capture or render. Requires account access. The panel uses view_capture to request a new image; models should use take_screenshot when they need to inspect current appearance.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "view_latest"
  }
}

Input Schema

Name	Required	Description
`since`	No	Last preview sequence already displayed by the panel.
`wait_ms`	No	Optional maximum wait for a view change, in milliseconds.
`instance_id`	No	Runtime instance last observed by the panel.
`scene_version`	No	Scene version last observed by the panel.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 23, 2026

addedInput schema / properties / instance_id / description

Added value: +"Runtime instance last observed by the panel."

addedInput schema / properties / scene_version / description

Added value: +"Scene version last observed by the panel."

addedInput schema / properties / since / description

Added value: +"Last preview sequence already displayed by the panel."

addedInput schema / properties / wait_ms / description

Added value: +"Optional maximum wait for a view change, in milliseconds."

First observedOct 23, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Beyond the readOnly/idempotent annotations, it discloses that no new capture is started, that wait_ms blocks up to 25 seconds (long-poll semantics), and that account access is required. These are useful operational traits not derivable from the annotation block, though the return shape of the counters is only loosely characterized.

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?

The disambiguating constraints and the 'does not start a new capture' boundary are front-loaded, and the alternative-tool guidance closes it cleanly. It is dense but each clause carries information; only the 'App-only adapter' framing is slightly redundant with the title.

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 zero required params, no output schema, and full schema coverage, the description covers scope, blocking behavior, prerequisites, and routing. The remaining gap is a slightly vague account of what the returned preview/counter payload contains, which matters given no output schema exists.

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 coverage is 100%, so the schema already documents all four parameters and the 25000 ms cap. The description largely restates those meanings ('since is the last preview sequence already displayed', 'scene_version and instance_id identify the panel's last known scene and runtime'), adding only mild framing about incremental polling and no format detail beyond the schema.

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 and resource ('reads the panel's latest existing preview and view-state counters') and immediately scopes it as an adapter for a panel's last-known state. It is clearly distinguished from view_capture (request new image) and take_screenshot (model inspection), so an agent can separate it from siblings without opening schemas.

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

Usage Guidelines5/5

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

Explicitly names both alternatives and the condition selecting each: 'The panel uses view_capture to request a new image; models should use take_screenshot when they need to inspect current appearance.' It also states a negative condition ('Does not start a new capture or render') and a prerequisite ('Requires account access').

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

All Blender Bridge 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?