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

Beyond the readOnly/destructive annotations, it discloses that absent originalData zero-scores the raw-fidelity dimension, warns against fabricating values, notes the published-only restriction, and states that no credits are consumed. This is significant operational behavior an agent needs to know.

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 dense but every sentence earns its place: purpose, identifier preference, originalData guidance, scoring consequence, pricing, and prerequisite resource. It is front-loaded with the action and then adds necessary operational context without padding.

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?

For a benchmark evaluation tool, it covers inputs, output metrics, prerequisites, error case, optional-data handling, and credit cost. With an output schema present, no return-shape detail is missing. An agent has everything needed to call this correctly.

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?

Even though schema coverage is 100%, the description adds decision-critical semantics: statement_id is preferred over content_hash, originalData is strongly recommended and should be passed through verbatim from get_statement, and omission has scoring consequences. This goes well beyond the schema field names.

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 ('Score') and resource ('parsed bank statement transactions against the Bankstatemently benchmark ground truth'), and names the concrete output metrics (extraction accuracy, integrity score, overall score). This clearly separates it from sibling tools like list_statements or rate_statement.

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?

It gives explicit preconditions — only published:true statements can be evaluated, held-out statements return an error — and directs the agent to read the benchmark://catalog resource first. It also recommends fetching originalData via get_statement with data_mode 'original', but does not explicitly enumerate when to choose this over sibling scoring/evaluation tools.

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