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

Beyond annotations (idempotentHint, destructiveHint), the description adds concrete behavioral details: idempotent application ('only real differences are written'), the forwarding-loop guard, and the business_hours derivation. These are useful and go beyond what annotations state. No contradiction with annotations; the destructiveHint aligns with 'Replace'.

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 description is long but every sentence carries necessary content: purpose, schema example, behavioral notes, usage prerequisite, and API reference. It is front-loaded with the purpose and structured logically. While dense, there is no filler or repetition.

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?

Given the complex nested 'flow' object, the description covers the full structure, idempotency behavior, guard, business hours derivation, and the prerequisite read-write pattern. An output schema exists, so return value details are not needed. It omits error cases or edge conditions but is sufficient for an agent to use it 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?

The schema only describes 'flow' as 'The complete phone flow to apply' with no structure. The description compensates fully by specifying the exact JSON shape, including version, hours mode, afterHours, ring members (with kind, phone, label, requirePressOne), timeoutSeconds range, overflow, and the enums for hours.mode. This is essential semantics not present in the schema.

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 clearly states a specific action ('Replace how calls ring') on a specific resource ('the business's hosted phone system') with a full phone flow. It distinguishes itself from the sibling 'get_phone_flow' by explicitly referencing it as the read counterpart, and the API mirror adds further precision.

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 an explicit prerequisite: 'Read the current flow with get_phone_flow first and send it back with your edits.' This is a clear usage guideline for the correct sequence, though it does not enumerate situations where the tool should not be used (e.g., when a simpler update is needed). The guidance is adequate for distinguishing from read operations.

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