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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so safety is covered. The description does add real behavior beyond that: what gets returned (understood inputs, explanation, assumptions, source_page, related_reading) and the need_more_info status with the exact follow-up question. However the 5-point scale is meant to reward richer disclosure, and it stops short of saying what happens when the question is ambiguous or matches multiple calculators, or how a need_more_info response should be relayed.

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 routing instruction is front-loaded and the return-value sentence is efficient. The six inline examples are somewhat repetitive and lengthen the definition, but they do double duty illustrating both the input style and the calculator coverage, so they mostly earn their place.

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?

With no output schema, the description carries the full burden of explaining return values and does so: answer plus understood inputs, explanation, assumptions, citation fields, and the need_more_info branch with a ready-to-ask question. Nothing an agent needs to call it or interpret the result is missing.

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?

Only one parameter with 100% schema coverage, so the baseline is 3–4 and the schema already carries the definition. The description adds useful meaning by explaining that amounts, rates, ages and years are parsed out of the free-text question, which tells the agent to pack those numbers into the string rather than send a bare topic.

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 specific verb+resource ("answer a money question") and immediately distinguishes itself from the calculate_* siblings by acting as the natural-language front door that picks and runs the matching calculator. The six worked examples make the intended input domain unmistakable.

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?

"Use first when a user asks a money math question in plain words" is an explicit routing rule that names the triggering condition and implies the alternative (call a specific calculate_* tool directly when the type is already known). It also enumerates the calculator families it will dispatch to, so the agent can tell when to bypass it.

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