remove_vllm

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states the config file mutation, the selective shutdown, and two important non-effects: other models stay up and weights remain on disk.

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?

Three concise sentences each add value: the core action, the scope, and the clarifying non-effect. The description is front-loaded and contains no redundant phrasing.

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?

Given no annotations and no output schema, the description covers the essential invocation semantics and side effects well. Minor gaps remain around error conditions, whether a restart is possible after removal, and which parameter is needed when both are optional.

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?

The input schema already documents both parameters with 100% coverage, so the baseline applies. The description loosely maps to model_id/backend_id but adds no extra detail about parameter precedence, combinations, or formats beyond what the schema provides.

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 uses specific action verbs ('stop' and 'unregister') with clear resources (vLLM instance, backend, specialist, agents.config.yaml). It also distinguishes itself from sibling operations by explicitly stating that downloaded weights are not deleted.

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 description clearly scopes the operation: it affects exactly one instance, leaves other running models up, and does not remove weights. It does not explicitly name alternative tools such as stop_vllm or delete_local_model, so it stops short of full alternative routing.

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