llm_route

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

No annotations are provided, so the description carries full burden. It discloses the internal classification tiers and routing logic, plus auto-detection of task_type. However, it does not mention authentication, rate limits, or failure behavior. Output schema exists but is not described, which is acceptable.

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 front-loaded with the core purpose, then splits into classification tiers and args. It is concise with a clear bullet list, no unnecessary words, and 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?

Given the 7 parameters and complexity, the description covers the main functionality, distinguishes from siblings, and provides an output schema. It could mention error handling or limitations, but overall it is reasonably complete.

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 0%, but the description adds meaning for all parameters, including temperature range and complexity_override options. It could be more detailed about allowed values for task_type and context usage, but it significantly compensates for the lack of schema descriptions.

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 tool is a 'smart router' that classifies task complexity and routes to the optimal external LLM. It specifies the verb 'routes' and the resource 'external LLM', and distinguishes itself from siblings like llm_classify.

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 usage guidelines are provided: it tells when to use this tool (for routing to external LLMs) and when not to (for Claude's own models, use llm_classify). It names an alternative tool, which is explicit guidance.

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