ypollak2/llm-router

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

With no annotations provided, the description carries the full burden of behavioral disclosure, detailing the classification algorithm (complexity tiers), budget pressure thresholds (0-85%, 85-95%, 95%+), downshift behavior, and return characteristics (budget usage bar). It transparently explains exactly how the recommendation logic works.

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 efficiently structured with purpose upfront, followed by return value description, algorithm logic with clear bullet points, and parameter documentation. Every section earns its place; the detailed budget pressure thresholds are essential behavioral context, not verbosity.

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 that an output schema exists, the description appropriately focuses on the classification algorithm and high-level return characteristics rather than field-by-field output documentation. The complex budget/complexity interaction logic is thoroughly explained, making it complete for a tool of this complexity.

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?

Despite 0% schema description coverage (only titles provided), the Args section fully documents all three parameters with semantic meanings and valid enum values ('best'/'balanced'/'conserve' for quality, 'haiku'/'sonnet'/'opus' for min_model). The description completely compensates for the schema's lack of 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 opens with 'Classify a prompt's complexity and recommend which model to use,' providing a specific verb and resource that clearly distinguishes it from sibling tools like `llm_generate` (content generation) and `llm_route` (routing). It further clarifies the scope by detailing the complexity-to-model mapping (simple→haiku, etc.).

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 establishes clear context for when to use the tool (complexity classification with budget awareness) and explains the decision logic thoroughly. However, it lacks explicit guidance on when *not* to use it versus specific alternatives like `llm_route` or `llm_generate`.

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