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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds nothing behavioral beyond that – no note on rounding/precision, how string inputs are parsed, or error behavior for incompatible mode/value combinations. The one useful addition is the margin-vs-markup distinction.

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?

A single front-loaded sentence led by the verb, with no filler or repetition of the title. It is a dense enumeration, but every clause maps to a real mode, so nothing is wasted.

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?

An output schema exists and the input schema is fully documented, so return-format explanation is not needed. With annotations covering safety and the enum covering modes, the definition is nearly self-sufficient; only precision/error-handling behavior is left unstated.

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?

Schema description coverage is 100%, including role assignment for a and b per mode, so the schema already carries the semantics. The description's re-listing of the modes largely duplicates the enum rather than adding meaning (e.g., it never clarifies the argument order for 'reverse' or how 'margin' consumes a and b). Baseline 3.

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?

States a concrete verb ('Calculate') plus the resource (percentage) and enumerates the exact computation modes offered, which cleanly separates it from the other calculators in the sibling list (calculate_cidr, calculate_emi, calculate_programmer). An agent can identify the tool's domain without opening the schema.

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 mode list implies which scenario each variant covers ('what percent one number is of another', 'percent change', 'margin versus markup'), giving some usage signal. But there is no explicit when-to-use/when-not statement and no routing to alternatives such as convert_units or calculate_programmer.

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