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

Annotations already declare read-only/idempotent, so safety is covered. The description adds genuine interpretive context beyond that: deltas are null when no comparable period exists, and totals mix currencies when currencyCount > 1, which the agent is told to surface. It does not discuss latency, cost or the size of the payload, but the critical caveat is present.

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?

Two short paragraphs, front-loaded with what is returned, then alternatives, then the precondition. Every sentence carries information the agent cannot get from the schema or annotations.

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?

Return shape is covered by the output schema, parameter format by the schema, safety by annotations, and the description closes the remaining gaps: comparison semantics, the currency-mixing pitfall, sibling routing, and the store-connected precondition.

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 100%, and the description's only parameter detail ('days', 30 by default) merely restates the schema default and enum. It gives no extra guidance on how from/to interact with days, leaving the schema to do all parameter work.

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?

Names the exact metrics returned (orders, gross/net revenue, refunds, units, AOV) plus the comparison window, so the agent knows precisely what call it is making. Siblings readTopProducts and readSalesTrend are named as the alternatives, making it distinguishable without opening any 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?

Explicitly routes to readTopProducts for best sellers and readSalesTrend for a day-by-day line, and states the precondition (workspace must have a store connected; listWorkspaces identifies them). Both when-to-use and when-not are covered.

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