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

Annotations already convey the mutation profile (readOnlyHint=false, destructiveHint=false). The description adds behavioral nuance beyond those flags: the search is keyword-based rather than requiring an exact model ID, and any OpenRouter model is accepted. This helps the agent understand partial matching behavior and the valid value space.

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 sentences with no filler. The primary action is stated first, followed by actionable search examples and a succinct scope statement about OpenRouter. Every sentence earns its place.

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 two-parameter setter with no output schema, the description covers the essential call semantics: what it does, how to search, and what values are valid. It doesn't describe success/failure return behavior, but that's a minor gap for a simple set operation.

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%, so the baseline is 3. The description adds value by giving concrete query examples ('opus', 'claude-sonnet', 'gpt-4o', 'deepseek', 'llama') and clarifying that keyword/partial matching is acceptable, going beyond the schema's generic 'Model name or keyword to search for'.

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 identifies the action ('Set') and resource ('preferred LLM model for an agent'). The verb is specific and unambiguous, and the focus on setting (as opposed to the sibling llm_get_model's getting) distinguishes the tool without needing to open the 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?

The description gives concrete usage context: search by name or keyword, with realistic examples. It establishes when to call this tool (when an agent's model needs to change) but does not explicitly mention the sibling llm_get_model or state when not to use it. Clear context with no exclusions earns a 4.

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