calculate_percentile_rank

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

No annotations are provided, so the description must fully disclose behavior. It incorrectly states inputs as 'dataset' while the schema expects counts, and does not explain how ties or edge cases are handled. This misrepresentation undermines 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 relatively short with three sentences, but the inconsistency between the stated inputs and the schema reduces its effectiveness. It is not overly verbose but could be clearer.

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 simplicity, the description should accurately convey the required inputs. The mismatch between described and actual inputs makes it incomplete for correct usage. The presence of an output schema (if true) is not documented, so the context remains insufficient.

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 all schema properties have descriptions, the tool-level description contradicts them by mentioning a 'dataset' input. The schema explanations are clear, but the description adds confusion rather than value, failing to accurately explain the actual parameters.

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 computes percentile rank for benchmarking purposes, and distinguishes it from other calculate tools. However, there is a mismatch between the described inputs ('dataset') and the actual schema (aggregate counts), which slightly reduces clarity.

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 a use case (benchmarking scores or salaries) and points to 'list_bundles' for related calculators. However, it lacks explicit guidance on when not to use this tool and does not compare with similar sibling tools like calculate_z_score.

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