partme_blender

Overview Schema Source Related Servers Discussions Admin

capability.describe

blender_capability_describe

Read-onlyIdempotent

Describe Blender environment capabilities and available operations for a given runtime profile. Use this to check which Blender features are accessible before executing commands.

Instructions

PartMe Blender Harness command capability.describe. Risk: read; maturity: L3. Requirements: Per-request argument checks and session policy still apply

Input Schema

TableJSON Schema

Name	Required	Description
`id`	Yes
`profile`	No
`runtime`	No
`platform`	No
`_requestId`	No	Stable request id for replay safety
`runtimeMode`	No
`_authorization`	No	Action-bound Harness authorization claim
`_transactionId`	No	Harness milestone transaction id
`blenderVersion`	No
`_expectedSceneRevision`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed18 schema fields changedv0.5.3Sep 22, 2026

removedInput schema / properties / blenderVersion / description

Removed value: -"See command validation; detailed type not yet audited"

addedInput schema / properties / blenderVersion / items

Added value: +{
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / blenderVersion / maxItems
```
Added value: +3
```
addedInput schema / properties / blenderVersion / minItems
```
Added value: +3
```
addedInput schema / properties / blenderVersion / type
```
Added value: +"array"
```

removedInput schema / properties / platform / description

Removed value: -"See command validation; detailed type not yet audited"

addedInput schema / properties / platform / type
```
Added value: +"string"
```
addedInput schema / properties / profile / additionalProperties
```
Added value: +false
```

removedInput schema / properties / profile / description

Removed value: -"See command validation; detailed type not yet audited"

addedInput schema / properties / profile / properties

Added value: +{
+  "excludeClasses": {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "excludeDomains": {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+}

addedInput schema / properties / profile / type
```
Added value: +"object"
```
addedInput schema / properties / runtime / additionalProperties
```
Added value: +false
```

removedInput schema / properties / runtime / description

Removed value: -"See command validation; detailed type not yet audited"

addedInput schema / properties / runtime / properties

Added value: +{
+  "architecture": {
+    "type": "string"
+  },
+  "blenderVersion": {
+    "items": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "maxItems": 3,
+    "minItems": 3,
+    "type": "array"
+  },
+  "platform": {
+    "type": "string"
+  },
+  "runtimeMode": {
+    "type": "string"
+  }
+}

addedInput schema / properties / runtime / required

Added value: +[
+  "blenderVersion",
+  "platform",
+  "architecture",
+  "runtimeMode"
+]

addedInput schema / properties / runtime / type
```
Added value: +"object"
```

removedInput schema / properties / runtimeMode / description

Removed value: -"See command validation; detailed type not yet audited"

addedInput schema / properties / runtimeMode / type
```
Added value: +"string"
```

First observedv0.1.0Sep 15, 2026

TDQS

D1.3/5.0

Behavior2/5

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

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the behavior profile is covered. The description adds 'Risk: read' (consistent with annotations) and 'maturity: L3' plus 'Per-request argument checks and session policy still apply', which are minor operational notes but do not explain what happens during the call, response characteristics, or side effects. It adds marginal value beyond annotations, so a 2 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short, but this is under-specification rather than efficient conciseness. It lacks any structure, front-loading of key purpose information, or meaningful content. The sentence is essentially a label with tangential notes, not a concise explanation. It fails to earn its place as a useful description.

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

Completeness1/5

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

Even though an output schema exists (so return values need not be explained), the description is fundamentally incomplete. It does not state what the tool does, when to use it, or how it differs from the 130+ sibling tools. For a read-only introspection command, an agent cannot infer the correct usage scenario or expected result from this description. It is inadequate for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 30%, leaving 70% of parameters' meaning unresolved by the schema. The description provides zero explanatory content for parameters like id, profile, runtime, or the underscore-prefixed internal fields. It does not compensate for the low coverage or clarify how parameters map to behavior. The generic phrase 'Per-request argument checks' offers no parameter-specific semantics.

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

Purpose1/5

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

The description restates the command name 'capability.describe' without explaining what the tool does. It provides no verb-resource phrasing, no indication of what capabilities are described, and offers no differentiation from sibling tools like blender_capability_list. This is a tautology.

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

Usage Guidelines1/5

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

No guidance is given on when to use this tool versus alternatives. The sibling blender_capability_list likely lists capabilities, but there is no explicit or implicit direction on when to call describe instead. The description only mentions generic requirement checks, not usage context.

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

Deploy Server