Fetch viewer session data, pending commands, or bounded geometry chunks for a scene. Specify scene ID and resource, then use offset to page through results.
App-only transport: session metadata, pending commands or bounded geometry chunks.
| Name | Required | Description | Default |
|---|---|---|---|
| offset | No | ||
| resource | Yes | ||
| scene_id | Yes | ||
| renderer_id | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds little beyond that—'app-only transport' is ambiguous about what the tool actually does with the data. There is no disclosure about return size, pagination behavior (despite the offset parameter), or any restrictions on use.
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 extremely brief (a single fragment), which might read as concise, but it is under-specified rather than efficiently informative. It lacks any structure or prioritization of key information. Conciseness is only valuable when the essential details are present, which they are not.
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?
Despite having an output schema (as indicated by context signals), the description does not leverage it or explain return values. With 4 parameters and a non-trivial purpose, the description is grossly incomplete. An agent cannot safely or correctly invoke this tool without external knowledge.
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?
Schema description coverage is 0%, and the description provides zero explanation of the parameters. Terms like 'resource', 'scene_id', 'offset', and 'renderer_id' are left entirely undefined. The description does nothing to help an agent understand what values are valid or what effect each parameter has.
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 is cryptic and does not clearly state what the tool does. It lists possible contents ('session metadata, pending commands or bounded geometry chunks') but does not use a clear verb like 'reads' or 'retrieves'. It fails to differentiate from sibling tools like inspect_3d_scene or list_3d_scenes, which likely also involve reading scene data.
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?
No guidance is provided on when to use this tool versus alternatives. The phrase 'app-only transport' hints at an internal purpose but is not elaborated, and no conditions or exclusions are mentioned. An agent has no idea when this is the appropriate tool to call.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.