benchmark-parsing

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses warmup iterations for JIT, multiple iterations for statistical accuracy, a performance rating framework, and optimization suggestions—giving the agent a comprehensive behavioral model.

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 well-structured with sections for when-to-use, measures, features, parameters, and an example. Every section earns its place, and the format makes it easy for an agent to parse quickly.

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?

Without an output schema, the 'Measures' section clearly explains expected return values (tokens, parse times, throughput, rating). The features and example make this a complete standalone description for a complex benchmarking tool.

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%, but the description adds meaningful relationships: it clarifies that grammar_content and from_file are alternatives, and provides a concrete example combining from_file with input. This goes beyond the schema's flat property list.

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 a specific verb+resource: 'Benchmark grammar parsing performance with sample input.' This clearly distinguishes the tool from siblings like compare-grammars or native-benchmark, and the 'Measures' section further clarifies its scope.

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 'When to use' section explicitly lists performance testing, grammar version comparison, and optimization validation. It provides clear usage context but does not explicitly exclude overlapping tools like profile-parsing or analyze-bottlenecks, so it stops short of a full 5.

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