start_late_infer

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

No annotations are provided, so the description carries the full burden. It discloses bind address restrictions, binary source, first-start loading behavior, and the non-auto-run approval wait. This gives an agent critical behavioral expectations beyond a bare 'start' verb, though it stops short of full lifecycle or status details.

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 compact sentences, front-loaded with the action and address constraint. Each subsequent clause adds a necessary caveat (binary source, first-start behavior, approval wait) without 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?

For a start command with no output schema and no annotations, the description covers endpoint, binary resolution, first-run model loading, and the non-auto-run approval behavior. It could mention status verification or what 'Late Approve' entails, but the essentials are present.

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 covers both parameters with descriptions (100% coverage), so the baseline of 3 applies. The main description ties model loading to Hugging Face safetensors, but adds limited parameter-level meaning beyond what the schema already 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?

States the action 'Start late-infer' plus resource/scope ('on this computer') and distinct endpoint constraint ('OpenAI /v1 on 127.0.0.1:8010 only'). This separates it from sibling start_* tools by naming the exact server and bind address, so an agent can identify what it does.

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?

Gives context: local-only launch, never LAN/0.0.0.0, and distinguishes first start from extra calls ('Extra calls wait for Late Approve — this is not auto-run'). It does not explicitly name alternatives like start_llamacpp/start_vllm, but the local endpoint and late-infer naming provide clear context.

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