ollama_pull

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

With no annotations provided, the description carries the full burden. It correctly identifies the action as downloading, implying a network operation, but does not disclose potential side effects, such as disk usage or time consumption. The description is accurate but lacks detail about behaviors like installation process, cache management, or progress feedback. There is no contradiction with annotations as none exist.

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 a single, concise sentence that directly states the tool's purpose with no extraneous information. It is front-loaded and efficient, earning its place without any wasted 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?

Given the tool's low complexity (1 parameter, no output schema, no nested objects), the description is adequate but minimal. It tells the agent what the tool does but does not explain return values (which models are pulled, success/failure indications) or constraints (e.g., requires network, model naming conventions beyond the example). For a simple tool, it covers basic functionality but lacks completeness in behavioral expectations.

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 has 100% description coverage, already documenting the only parameter with an example ('llama3.2, codellama'). The description adds no further param value but neither is needed; the schema fully covers it. The tool has a single parameter, so baseline is high. The example in the schema provides useful context beyond a mere name.

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 ('Download/pull') and the resource ('a new model from Ollama registry'). It effectively communicates the core purpose of the tool, which is to retrieve a model. While it lacks specific differentiation from sibling tools like ollama_list or ollama_info, the verb 'pull' indicates downloading a model compared to listing or showing info, though it could be more explicit.

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 implies usage for downloading models, which is clear from the context. However, it provides no guidance on when to use this tool versus alternatives, such as when a model is not available locally (vs ollama_list) or when running a model (vs ollama_run). It does not set expectations about prerequisites, like internet connectivity, or when not to use it.

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