benchmark

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

With no annotations, the description carries the full burden. It discloses the return format (one ParseResult per backend with latency, byte counts, error state, metadata) and notes it is a diagnostic tool, which suggests a read-only, non-destructive operation. However, it does not mention potential cost/performance implications of running all backends, nor does it clarify whether it modifies anything (though diagnostic implies it does not).

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 two sentences with the primary action front-loaded. It is efficient and avoids redundancy. Every sentence adds value: the first states the operation, the second clarifies it as diagnostic and details the output.

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?

The tool has a single required parameter, and the description fails to explain what that parameter is. While the output structure is partially described (ParseResult fields), the input format is a critical gap. The description also assumes the agent knows what 'backend' means, though sibling tool list_backends may help. Overall, this is incomplete for safe invocation.

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 schema has no description for the 'source' parameter and schema_description_coverage is 0%, so the description must explain it. The description never mentions 'source' or what input is expected. The phrase 'same input' is generic and does not clarify that 'source' is the document to run through backends. The agent has no basis to know what to provide.

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 states a clear, specific function: 'Run every available backend on the same input, compare results.' It also explicitly adds the word 'Diagnostic tool,' reinforcing its role as a comparison/benchmark rather than a typical parser. This distinguishes it from siblings like parse or parse_url, which are single-backend operations.

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 labels the tool as diagnostic and explains what it does (runs all backends and compares), which implies use cases like performance or correctness comparison. However, it does not explicitly say when NOT to use it or name alternatives (e.g., 'use parse for a single backend'), so the guidance is implicit rather than explicit.

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