stop_vllm

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

With no annotations provided, the description carries the burden of behavioral disclosure. It explains conditional failure ('the call fails unless all=true'), scopes the operation to orchestrator-managed instances, and clarifies the leftover orch-vllm edge case. It does not detail the exact stopping mechanism or what happens if the target is not found, but the core behavior is transparent.

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?

The description is four sentences, front-loaded with the primary action and scope, and every sentence adds unique value. There is no repetition or filler.

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 or output schema, the description covers the main invocation logic, key failure mode, and scope exclusions. Minor ambiguities remain, such as behavior when exactly one instance is running with no id set, but the overall guidance is sufficient for correct use in most cases.

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 schema already documents all three parameters, but the description adds valuable semantics: pass model_id or backend_id to leave other running models up, and all=true bypasses the failure when no id is set. This goes beyond the simple property descriptions in the schema.

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 clearly states the action ('Stop one orchestrator-managed vLLM instance') and identifies the resource type ('container or host process group'). It also explicitly excludes unrelated Docker containers, which differentiates its scope from broader stop operations.

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?

Provides concrete guidance on when to pass model_id or backend_id, and when all=true is required. It also includes an important exclusion ('Does not stop unrelated Docker containers'). However, it does not explicitly discuss alternatives like remove_vllm or describe when a user should prefer a different tool.

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