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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent, closed-world write. The description adds the behaviorally important detail that the task is created without prompting the user, plus the default 1-day deadline. It does not warn that repeat calls create duplicate tasks despite idempotentHint=false, so it falls short of full disclosure.

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?

A single tight sentence with the support-desk scope tagged up front and no filler. It is dense but front-loaded and readable in one pass; only the slight run-on in the middle clause costs it a point.

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 values need no explanation, and the core task shape is described. But for an 8-parameter tool with a nested customer object and three undocumented parameters, the description does not fully equip an agent to populate a correct call, nor does it mention account selection or duplicate avoidance.

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 only 13% (just the account param), so the description has to carry the load. It does map four of the eight inputs — topic, assignee ('responsible person'), due_days ('1-day deadline'), and the customer phone — but leaves order_ref, thread_id, and preferred_time entirely unaddressed in both places.

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 a specific artifact (an internal callback task) and enumerates its composition: phone, topic, responsible person, 1-day deadline. That is concrete enough to distinguish it from tasks_list or order-related siblings, though it never states the verb 'creates' explicitly and never names the sibling it differs from.

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 trigger is stated plainly: 'When a customer asks to be called.' That is a clear use condition, and 'Created without asking' tells the agent not to seek confirmation first. It stops short of naming exclusions or pointing at an alternative (e.g., tasks_list for reading existing tasks).

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