Install model

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

Annotations already declare destructive=true, non-idempotent and open-world, and the description adds real context on top: the confirm=true write gate (default is preview), the host allowlist restricting names to registry.ollama.ai bare names or hf.co/ paths, and the service restriction. This is exactly the kind of constraint detail annotations cannot express.

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?

Five short sentences, front-loaded with the action and mechanism, then constraints, then the confirm gate. Slight redundancy in the closing sentence about the JSON return shape, since an output schema already exists, but nothing else is wasted.

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 mutating, non-idempotent pull operation the description covers the mechanism, the confirmation requirement, the host/service allowlist, the sibling to consult for sizing, and return shape. With an output schema present it does not need to explain return values further.

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 100%, so the schema already documents model, confirm and service, including the same host restriction and the local_ai-only rule. The description restates those constraints rather than adding meaning beyond them, so the baseline 3 applies.

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 (pull/install) and resource (model) plus the exact mechanism (Local AI, Ollama-compatible /api/pull). It also carves out scope against siblings by naming recommend_model for size selection and declaring that MLX and Llama.cpp have no pull API, so an agent can distinguish it without opening a schema.

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?

Explicit routing to recommend_model for picking a size, an explicit exclusion (MLX/Llama.cpp not supported here), and a prerequisite gate ('Needs confirm=true to write') that tells the agent the call is a preview unless confirmed. Both when-to-use and when-not-to-use are covered.

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