Inspect which Ollama models are currently claiming NVIDIA GPU VRAM, for all models or one, so you can decide what to unload and free memory.
See who's claiming what right now (all models, or one).
| Name | Required | Description | Default |
|---|---|---|---|
| model | No |
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes | ||
| claims | Yes | ||
| outcome | Yes | ||
| summary | Yes | ||
| operations | Yes |
Changes observed during successful MCP inspections.
v0.3.1Output schema / (root)Previous value: -nullNew value: +{
+ "$defs": {
+ "ClaimEntry": {
+ "properties": {
+ "claim_id": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Claim Id"
+ },
+ "claimed_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Claimed At"
+ },
+ "expires_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Expires At"
+ },
+ "gb": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Gb"
+ },
+ "kind": {
+ "enum": [
+ "model",
+ "reservation"
+ ],
+ "title": "Kind",
+ "type": "string"
+ },
+ "model": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Model"
+ },
+ "owner": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Owner"
+ },
+ "pid": {
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Pid"
+ },
+ "purpose": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Purpose"
+ },
+ "renewed_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Renewed At"
+ },
+ "ttl_seconds": {
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Ttl Seconds"
+ }
+ },
+ "required": [
+ "claim_id",
+ "kind",
+ "model",
+ "gb",
+ "pid",
+ "owner",
+ "purpose",
+ "claimed_at",
+ "renewed_at",
+ "ttl_seconds",
+ "expires_at"
+ ],
+ "title": "ClaimEntry",
+ "type": "object"
+ },
+ "OperationEntry": {
+ "properties": {
+ "expires_at": {
+ "title": "Expires At",
+ "type": "string"
+ },
+ "kind": {
+ "title": "Kind",
+ "type": "string"
+ },
+ "lease_expired": {
+ "title": "Lease Expired",
+ "type": "boolean"
+ },
+ "lifecycle": {
+ "enum": [
+ "in_flight",
+ "unknown",
+ "unrecognized"
+ ],
+ "title": "Lifecycle",
+ "type": "string"
+ },
+ "model": {
+ "title": "Model",
+ "type": "string"
+ },
+ "operation_id": {
+ "title": "Operation Id",
+ "type": "string"
+ },
+ "outcome": {
+ "anyOf": [
+ {
+ "const": "unknown",
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Outcome"
+ },
+ "owner_live": {
+ "title": "Owner Live",
+ "type": "boolean"
+ },
+ "pending_until": {
+ "title": "Pending Until",
+ "type": "string"
+ },
+ "reason": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Reason"
+ },
+ "retry_after": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Retry After"
+ },
+ "retry_count": {
+ "title": "Retry Count",
+ "type": "integer"
+ },
+ "scope": {
+ "title": "Scope",
+ "type": "string"
+ },
+ "started_at": {
+ "title": "Started At",
+ "type": "string"
+ }
+ },
+ "required": [
+ "operation_id",
+ "model",
+ "kind",
+ "scope",
+ "started_at",
+ "expires_at",
+ "pending_until",
+ "lifecycle",
+ "owner_live",
+ "lease_expired",
+ "outcome",
+ "reason",
+ "retry_count",
+ "retry_after"
+ ],
+ "title": "OperationEntry",
+ "type": "object"
+ }
+ },
+ "properties": {
+ "claims": {
+ "items": {
+ "$ref": "#/$defs/ClaimEntry"
+ },
+ "title": "Claims",
+ "type": "array"
+ },
+ "ok": {
+ "title": "Ok",
+ "type": "boolean"
+ },
+ "operations": {
+ "items": {
+ "$ref": "#/$defs/OperationEntry"
+ },
+ "title": "Operations",
+ "type": "array"
+ },
+ "outcome": {
+ "enum": [
+ "succeeded",
+ "refused",
+ "failed",
+ "unknown"
+ ],
+ "title": "Outcome",
+ "type": "string"
+ },
+ "summary": {
+ "title": "Summary",
+ "type": "string"
+ }
+ },
+ "required": [
+ "ok",
+ "outcome",
+ "claims",
+ "operations",
+ "summary"
+ ],
+ "title": "ListClaimsResult",
+ "type": "object"
+}v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It conveys only that this is a read of current state; it says nothing about permissions, rate limits, pagination, or how staleness/emptiness of results behaves.
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?
One short, front-loaded sentence with no filler and the scoping clarification in parentheses. It is efficient, though arguably terse enough to leave gaps.
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?
The tool is simple (one optional param) and an output schema exists, so return values need not be described. Still, the description gives no routing context among the many claim-related siblings (claim, reserve, renew, release), leaving the agent to infer when this list view is appropriate.
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 single parameter is only labeled 'Model' with a null default. The description compensates by explaining the parameter's effect: passing a model scopes to one, omitting it covers all models — exactly the semantics the schema lacks.
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?
States a specific verb and resource: 'See who's claiming what right now' clearly indicates a read of current claim holders, and '(all models, or one)' gives the scope. It implicitly distinguishes itself from sibling list_loaded (loaded models vs claims), though it never names that sibling explicitly.
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?
The phrase 'all models, or one' implies when to pass the model argument versus omitting it, and 'right now' implies a real-time snapshot. But there is no explicit when-to-use guidance relative to list_loaded, history, or trend, and no exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.