Skip to main content
Glama

create_session

Start or reconnect to a remote Blender project session, restoring its last checkpoint and optionally choosing GPU, GUI/headless mode, or a new workspace.

Instructions

Start or reconnect to a project. GPU resources incur charges until stopped.

First creation builds a Blender image and can take several minutes. Existing
projects restore their last checkpoint. Set restore_revision to recover an older
checkpoint at startup if the latest one is unusable; stop any active session first.
new_workspace=true creates a new independent Blender/Sandbox/Volume, even for the
same project label. Returned workspace_id can reopen that exact workspace later.
Without either option, the default project workspace is reused. Agent spawning,
scheduling and aggregation are entirely the caller's responsibility.

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": {
      "project": "<project>"
    },
    "name": "create_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
gpuNo
modeNoheadless
projectYes
idle_secondsNo
workspace_idNo
new_workspaceNo
lifetime_secondsNo
restore_revisionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does substantial work: it warns that GPU resources incur charges until stopped, that first creation builds a Blender image and may take minutes, that existing projects restore their last checkpoint by default, and that agent spawning, scheduling and aggregation are out of scope. It still omits how idle_seconds and lifetime_seconds govern auto-termination, which is the actual mechanism behind the cost warning, and says nothing about failure or auth behavior.

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 cost warning and creation latency are front-loaded, then the recovery/workspace options are addressed in sequence, ending with the scope disclaimer. The length is justified by eight parameters, though "Without either option, the default project workspace is reused" restates earlier content and could be tightened.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an eight-parameter, annotation-free provisioning tool this covers cost, latency, checkpoint restore, and workspace identity, which is the right shape of information. The gaps are meaningful though: the semantics of idle_seconds and lifetime_seconds, and the headless/gui mode distinction, are exactly what an agent needs to control spend and interaction, and no output schema exists to fill them in.

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 0%, so the description must compensate, and it explains four of eight parameters: restore_revision (with the pattern-relevant constraint of stopping the session first), new_workspace, workspace_id (reopen the exact workspace), and project implicitly. It adds nothing about mode (headless vs gui), gpu enum choices, idle_seconds, or lifetime_seconds, so half the surface remains undocumented.

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?

"Start or reconnect to a project" gives a specific verb pair and resource, and the body clarifies that it provisions a workspace with optional GPU. It does not differentiate itself from the sibling open_project, so an agent cannot fully rule out the alternative from this text alone.

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

Usage Guidelines3/5

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

The description does give conditional guidance for parameter choices (restore_revision when the latest checkpoint is unusable, new_workspace=true for an independent Blender/Sandbox/Volume, otherwise the default workspace is reused), plus the prerequisite "stop any active session first." It never states when to call this versus open_project or list_sessions, so tool-level selection is left implied.

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