refund_rate

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

With no annotations, the description carries the behavioral burden and does disclose non-obvious traits: that start/end filter on order-placement date rather than refund date, and that low-volume groups produce statistically unreliable rates. It says nothing about permissions, cost, or row limits, but the read-only nature of an aggregate metric query is self-evident from the text.

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?

Three short sentences, each earning its place: metric definition first, then filter semantics, then the interpretation caveat. Zero filler and correctly front-loaded.

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?

The presence of an output schema means return values need no explanation, and the description covers what is computed, how grouping works, and how dates are applied. The remaining gap is the undocumented date/timestamp format for start and end, which an agent must guess.

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 0%, so the description must compensate. It explains the semantics of `by` (grouping dimension) and clarifies that start/end filter on order placement date, which is real added meaning, but it never states the accepted date string format or defaults, leaving half the parameters underspecified.

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 defines the exact computation ('refunded dollars as a percentage of revenue, plus units sold and refunded, grouped by `by`'), which is a specific metric that is immediately distinguishable from sales_summary or top_customers. An agent knows precisely what number this tool returns 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?

Usage is implied by the metric definition, and the description adds a genuine analytical caveat ('small groups can show extreme rates; check units_sold before drawing conclusions'). However, it never names an alternative or states when to prefer another sibling, and no when-not conditions are given.

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