Evict an Ollama model from VRAM to free GPU memory; specify a target from config or omit it for the default.
[WRITE][risk=medium] Evict a model from VRAM (keep_alive:0).
Args: model: Model name to unload. target: Ollama target name from config; omit for the default.
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | ||
| target | No |
Changes observed during successful MCP inspections.
v0.6.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=true and idempotentHint=false, so safety is covered. The description adds real value beyond them by disclosing the mechanism (keep_alive:0) and a 'risk=medium' signal, telling the agent exactly how eviction is performed rather than just that it mutates state.
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?
Front-loaded with the write/risk classifier and the core action before the Args block, with no wasted prose. The Args section slightly restates the header's intent but is compact and scannable.
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?
For a low-complexity two-parameter write tool with no output schema and annotations covering the safety profile, the description supplies purpose, mechanism, and both parameter meanings. The only material gap is the unaddressed overlap with the remove_model sibling.
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%, so the description must carry the load — and it does, documenting both parameters: 'model' as the model name to unload and 'target' as an Ollama target from config, including the important 'omit for the default' behavior that the schema does not convey.
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+resource: 'Evict a model from VRAM (keep_alive:0)' — an agent immediately knows this frees GPU memory rather than deleting a model. However, it never distinguishes itself from the very similar sibling remove_model, leaving the agent to infer that 'unload' is memory-eviction and 'remove' is disk-deletion.
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?
Usage is implied by the header tag '[WRITE][risk=medium]' and the VRAM-eviction phrasing, so an agent can infer it's for freeing memory. But there is no explicit when/when-not guidance and no pointer to the near-identical remove_model sibling, which is exactly the ambiguity that needed resolving.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.