llm_benchmark

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

With no annotations provided, the description bears the full burden. It discloses that accuracy is based on user ratings (llm_rate) and that an optional community export status is shown if LLM_ROUTER_COMMUNITY=true. It does not mention data freshness, aggregation period, or any side effects. While it avoids contradictions, more behavioral details (e.g., real-time vs cached) would improve transparency.

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 concise: three sentences with no wasted words. The first sentence front-loads the primary purpose, followed by necessary context about accuracy computation and an optional feature. 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?

Given no required parameters and an existing output schema, the description covers the essential aspects: what is shown (benchmarks by task type), how accuracy is derived (from llm_rate feedback), and a conditional element (community export). It is reasonably complete for a display tool, though it could mention expected output format or time range covered.

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 tool has no parameters, so the input schema is empty (100% coverage, baseline 4). The description adds value by explaining what the tool shows (benchmarks, community export status) and the data source, which is beyond what the empty schema provides. Thus, it fully compensates for the lack of parameter details.

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's purpose: 'Show routing accuracy benchmarks by task type.' It uses a specific verb ('Show') and resource ('routing accuracy benchmarks by task type'), effectively distinguishing it from siblings like llm_rate (for rating) and llm_model_eval.

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 provides context about the data source (accuracy computed from llm_rate feedback) and notes that rating more improves accuracy, implying when it becomes more useful. However, it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or best practices. The guidance is implied but not explicit.

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