percentage

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

With no annotations, the description carries the entire behavioral burden, and it does a good job for a pure calculation: it states the crucial whole-must-be-zero error condition and notes that the result is a string. It does not describe the exact exact formatting (e.g., decimal places or percent sign), but that can be supplied by the output schema.

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 short and front-loaded: a single purpose sentence, preceded by a compact Args/Returns breakdown. Every sentence or chunk contributes to purpose, parameter interpretation, return behavior, or an edge case.

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 two-number math operation, the description is adequately complete: it covers the core computation, parameter meanings, the error-on-zero case, and the return kind. The only notable missing detail is the exact textual format of the returned percentage (e.g., decimal precision, '%' sign), which the output schema may already communicate.

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 0% description coverage, so the description is fully responsible for explaining both parameters. It defines part as 'the partial amount' and whole as 'the total amount', and it adds the necessary constraint that whole must not be zero. This adds real meaning that the bare number-typed schema does not 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 clearly states the action—'Compute what percentage part is of whole'—with specific roles for both arguments. The operation is visually distinct from the sibling math tools (add, subtract, multiply, divide, power, square_root), so an agent can tell which tool to invoke.

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?

Usage is only implied by the tool name and definition; the description does not say when to prefer it over, say, divide, or when not to use it. However, the phrase 'Compute what percentage' gives enough context that an agent can probably apply it correctly.

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