complete

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

No annotations are provided, so the description must fully disclose behavior. It covers: data locality ('data never leaves the machine'), streaming via MCP progress notifications, default streaming behavior (true), and first-detected-provider fallback. Missing error handling details, but core safety and flow are documented.

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?

Four sentences, each purposeful: labeled purpose, usage warning, parameter guidance, streaming behavior. Front-loaded with bold 'DELEGATED INFERENCE:' for quick scanning. No unnecessary words.

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?

Lacks description of return value (e.g., completion text or stream chunks). With no output schema, this is a gap. Otherwise covers key aspects: purpose, usage, streaming. Moderate complexity (8 params) handled well but incomplete on response format.

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 coverage is 100%, baseline 3. Description adds significant value: clarifies that prompt and messages are alternatives, explains default provider behavior, and details streaming mechanics (progressToken, default true). These enrich schema definitions without redundancy.

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 explicitly states 'DELEGATED INFERENCE: Offload a text/chat completion to a local model runtime' with a clear verb and resource. It distinguishes from sibling tools like 'embed' or 'suggest_model' by specifying local model runtime and non-user-chat nature.

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?

Includes a clear exclusion: 'This is NOT a chat feature for the user.' Specifies alternative inputs ('Provide either prompt or messages') and default provider behavior. Lacks explicit comparison to sibling inference tools like 'embed' or 'suggest_model', but context makes role clear.

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