Evaluate Benchmark

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

Beyond the annotations (readOnly, non-destructive), the description discloses additional behavioral aspects: it is free (no credits consumed), held-out statements return an error, and omitting originalData scores that dimension 0 rather than fabricating values. These details make the tool's side effects and scoring behavior explicit.

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 substantial but every sentence serves a purpose: stating the function, identifying inputs, specifying constraints, and giving warnings. No redundant filler or repetition. It is information-dense while remaining readable and well-structured.

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 tool's complexity (multiple parameters, nested objects, and nuanced scoring rules), the description covers all essential aspects: the need for published status, the role of originalData, the error behavior, and the free usage. It provides enough context for an agent to call the tool correctly without additional information.

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?

Although the schema already covers all parameters (100% coverage), the description adds meaningful semantics: it explains the preference order between statement_id and content_hash, and elaborates on the originalData parameter's purpose and consequences of absence. This goes beyond the schema's basic field descriptions and clarifies the intent behind each key parameter.

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 uses the specific verb 'Score' and clearly states the resource (parsed bank statement transactions against the benchmark ground truth). It also distinguishes itself by mentioning the accepted identifiers (statement_id or content_hash) and the required transactions, making the tool's purpose unmistakable even without the name.

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 explicit guidance on when to use the tool: only for statements marked published:true in the catalog, and it instructs to read the benchmark://catalog resource first. It also advises preferring statement_id over content_hash and recommends fetching originalData via get_statement, giving clear directions for correct usage.

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