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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered; the description still earns credit by stating 'does not reserve time — ORS Clean confirms one window directly,' which tells the agent the side effect is zero and a human confirms. It also notes the out-of-area path (service-area message instead of a grid). It stops short of describing the shape of a returned grid, which is the remaining gap.

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 core instruction is front-loaded and the trigger-phrase list is functional, but the twelve-city enumeration and the long quoted customer-phrase run-on add bulk that the schema/sibling tools could carry. It is longer than it needs to be for three optional parameters.

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 three-optional-parameter, read-only lookup with no output schema, the description covers purpose, trigger, ordering against request_quote, and the non-reserving side effect. Only the returned format (how windows appear in the grid) is left implicit, which is a minor omission rather than a blocker.

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%, so the baseline is 3; the description adds workflow meaning by explaining why the agent collects windows ('so the customer can name up to three preferred windows') and that they are carried forward as preferred_slots on request_quote. That cross-tool parameter linkage is genuinely beyond the schema, though the preferred_slots name does not exist on this tool and could briefly confuse.

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 opens with a specific verb and resource ('Returns ORS Clean's open morning (8–12) and afternoon (12–4) service windows for the next two weeks') plus a concrete geography. It is unmistakably distinct from siblings like check_service_area and request_quote, and the scope (two-week horizon, two named window types) is stated up front.

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?

It gives explicit trigger conditions with worked customer phrasings ('when are they free / soonest appointment'), an ordering rule ('before request_quote'), and a negative instruction ('Do NOT answer availability from memory or a generic lead-time'). That is when-to-use, when-not-to-substitute, and the alternative workflow all in one place.

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