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

Annotations already reveal readOnlyHint=false (mutation), openWorldHint=true, idempotentHint=false. The description adds context that the tool 'creates a callback lead, not an appointment' and does not handle emergencies. This goes beyond the annotations by clarifying the type of side effect (lead creation) and what it does not do, which is valuable for an agent deciding among similar tools.

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 sentences, no wasted words. The primary use condition is front-loaded, followed by a clarification of what the tool creates and a clear exclusion with a fallback action. Every sentence contributes to correct selection and usage.

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?

The description covers the essential context: the trigger condition, the type of result (lead vs appointment), and the emergency exclusion. There is an output schema present, so return value details need not be in the description. The only minor gap is not detailing optional parameters like preferred_callback_time, but those are self-explanatory and covered by the schema. Overall sufficient for an agent to use correctly.

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 71% (5 of 7 params documented). The description does not explicitly reference specific parameters by name but implies the requirement for contact details ('their own contact details') and the confirmed flag via 'explicitly asks'. It adds minimal semantic value over the schema, which already covers most parameters. Baseline of 3 is appropriate given high schema coverage.

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 uses a specific verb ('request a callback') and names the resource (Johnson Bros. callback). It clearly distinguishes this from an appointment and from emergency dispatch, which sets it apart from sibling tools like request_booking and emergency_help. The purpose is unambiguous.

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 description explicitly states when to use it: 'only after the user explicitly asks Johnson Bros. to call them' and that the user must provide their own contact details. It also gives a clear exclusion: 'Do not use it for emergency dispatch' and directs emergency users to call a phone number. This is model guidance for when/when-not to use the tool.

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