sales_summary

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

With no annotations, the description carries the full behavioral burden and does it well: it discloses that only completed orders count, refunds are attributed to the original order's date, weeks start Monday, and a totals row with average order value is appended. These are non-obvious business rules an agent could not infer from the schema; only auth/rate-limit context is absent, which is minor for a read tool.

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 opening sentence is front-loaded with what the tool returns, and each following sentence adds a distinct rule (date bounds, completed-only, refund attribution, week start, totals row). Dense with zero filler, though the terse fragment style slightly reduces readability.

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, so return-shape explanation is not required, yet the description still adds the totals-row/AOV detail. Business logic is thorough; only the undocumented group_by default and any permission requirements are missing, which is a small residual gap for a 3-param aggregation tool.

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 0%, so the description must compensate, and it largely does: start/end are defined as inclusive YYYY-MM-DD with 'leave either out for no bound,' which is genuinely useful. group_by is only indirectly covered ('time period or dimension' maps onto the enum values), and the default of month is never stated, leaving one small gap.

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 names the resource (sales metrics: orders, units, revenue, refunds, net revenue) and the aggregation axis (time period or dimension), so an agent knows exactly what it computes. It does not explicitly contrast itself with siblings like run_sql or top_customers, but the scope is specific enough to route on.

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 only implied: the metrics list and grouping options suggest 'use this for aggregated sales reporting,' but there is no explicit when-to-use, no exclusions, and no mention of the obvious alternative (run_sql) present in the sibling list. The date-bound behavior hints at scope but is not framed as guidance.

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