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

Beyond the annotations (idempotentHint=true, destructiveHint=false), it discloses the operational consequences: messages are always stored, sms.received always fires, the external system replies via send_message or POST /v1/messages, and re-sending the same owner is a no-op. These are exactly the traits an agent needs but cannot read off the structured fields.

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?

Dense but front-loaded and free of filler; each sentence carries a distinct fact (mode semantics, timeout, persistence, scope, idempotency). It is on the long side, but nothing is redundant enough to cut without losing behavioral detail.

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?

With an output schema present, return values need no explanation, and annotations already cover the safety profile. Between the mode semantics, scoping rules, timeout bounds and handoff behavior, the description is complete for correct invocation.

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 ~80%, so the baseline is 3, and the description adds real value: the timeout range (60-86400), the external-only constraint, and the business_id requirement when only phone is given. This meaningfully extends what the schema states.

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?

States a specific verb and resource ('Set who answers a customer's text conversation') and then defines each owner value ('ai', 'human', 'external') with distinct meaning. An agent can immediately tell what routing change this makes and how it differs from plainly named siblings like set_owner_phone.

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 clearly explains when each mode applies ('ai' default replies, 'human' stays quiet, 'external' hands off to the business system) and how to scope the change via conversation_id or phone. It stops short of naming an alternative sibling for related routing tasks, but the mode-by-mode context is explicit.

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