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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds genuine behavioral context beyond that: responses can be large, offset paging terminates when next_offset is null, and dates are interpreted in UTC. It stops short of describing result ordering, default page size behavior, or what a sale record contains.

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 dense sentences with no filler: filters first, then paging mechanics, then the escalation path to sales_summary. The most decision-relevant information (filters and the alternative tool) is 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?

For a 12-parameter, no-output-schema search tool, it covers the two things the schema cannot: pagination continuation and the existence of a cheaper aggregation alternative. It does not say whether filters combine with AND, what the default ordering is, or that page_size defaults exist, but those are minor against the strong schema coverage.

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 92%, so the schema already documents nearly every parameter including UTC date interpretation and the payment type config_id. The description mostly restates the filter list and adds only the paging continuation convention, which is close to baseline for a high-coverage schema.

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?

Opens with a specific verb and resource ('Find sales') and enumerates the filterable dimensions plus the underlying endpoint. It distinguishes itself from sales_summary for the totals case, but never states how it differs from the sibling list_sales, which an agent must infer.

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?

Explicitly routes the agent away from this tool when period totals are wanted ('use sales_summary instead of paging through this'), and explains how to continue paging. It gives clear context but no exclusions or guidance relative to list_sales or get_sale.

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