lilbee

Overview Schema Source Related Servers Discussions Admin

set_placement

Assign specific GPUs and optional tensor splits to roles like chat, embed, rerank, or vision, then persist the manual multi-GPU placement to config.

Instructions

Set and apply a manual multi-GPU placement spec (persists to config).

Maps a role ("chat"/"embed"/"rerank"/"vision") to a placement, e.g. {"chat": {"devices": [0, 1], "tensor_split": [1, 1]}}. devices is the GPU indices (get_gpus lists them); tensor_split is optional per-device weights (omit for an even split). A role left out is auto-placed.

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": {
      "spec": "<spec>"
    },
    "name": "set_placement"
  }
}

Input Schema

Name	Required	Description	Default
`spec`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.0.3Jul 24, 2026

TDQS

A4.1/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It usefully discloses persistence to config, the auto-placement of omitted roles, and that tensor_split defaults to an even split. It does not say whether changes apply immediately, require a reload/restart, or how they interact with existing placements, which are meaningful gaps for a mutating tool.

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

Conciseness5/5

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

Front-loaded with the core action and persistence note, then a compact example and two clarifying clauses. Every sentence earns its place; nothing is redundant.

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?

Output schema exists, so return values need not be described. The high-complexity nested payload is well documented. Only minor behavioral details (apply timing, reload requirement, override semantics) are absent for a no-annotation mutation tool.

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

Parameters5/5

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

Schema coverage is 0% and the sole param 'spec' is an opaque bare object, so the description does all the work: it gives the role→placement shape, a concrete example, and the meaning/default of 'devices' and 'tensor_split'. This fully compensates for the schema and is exactly what an agent needs to build the payload.

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+resource ('Set and apply a manual multi-GPU placement spec') with the added scope qualifier that it persists to config. Together with the role-mapping explanation, an agent can distinguish it from get_placement/preview_placement/clear_placement without opening any schema.

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?

Usage is implied rather than stated: 'manual' placement and 'persists to config' signal this is the durable counterpart to preview_placement/get_placement, but the description never explicitly says when to prefer it over those siblings or whether preview should be run first. Adequate but leaves routing to inference.

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