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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful context about the returned components (net amount, count, itemized lines) but does not disclose details such as whether itemized lines are always present, how currency is handled, or any aggregation quirks.

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 that immediately communicates the resource and the main output fields. Every word earns its place, with no filler or repetition of the title.

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 read-only, no-required-parameter report, the description is largely sufficient: it names the core returned data and the annotations cover safety. The absence of an output schema is partially mitigated by listing the refund components, though the exact shape of itemized lines remains unspecified.

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 coverage is 75%, so most parameters are already documented in the schema. The description reinforces the date-window concept, which maps to date_from/date_to, but adds no new meaning for currency or seller_connection_id beyond what the schema provides.

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 identifies a specific resource — refund components — and lists the key outputs: net refund amount, count, and itemized lines. It is clearly about refunds within a date window, which helps distinguish it from other pnl_* siblings, though it does not explicitly name any alternative.

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 phrase 'for a window' implies date-range usage, and the title signals this is a refund detail report. However, there is no guidance on when to choose this over closely related siblings like pnl_breakdown, pnl_summary, or pnl_settlement_audit, and no exclusions or prerequisites are stated.

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