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

Annotations already declare the safety profile (not read-only, not destructive, non-idempotent, closed-world), so the description only needs to add context. It explains the gating dependency on create_business/request_payment, but does not say what actually happens on call — whether a WhatsApp message/code is sent, how the result is observed, or why non-idempotent repeats matter. The 'show a button' framing also undersells the non-read-only side effect.

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?

Two short sentences, front-loaded with the action and followed by the prerequisite condition. No filler and the parenthetical trigger codes are placed where the agent will see them.

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 zero-parameter, no-output-schema tool with annotations, this covers the essential prerequisite and the error that triggers it. It is slightly short on what the caller/user must do after the button appears and how completion is confirmed.

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 tool takes zero parameters, so there is nothing for the description to disambiguate and the schema is trivially complete. Baseline of 4 applies.

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 states the concrete action ('Show a Verify on WhatsApp button') for a specific resource (WhatsApp verification) and implicitly distinguishes it from the sibling remove_whatsapp. The verb choice 'show' versus the tool name's 'request' leaves a small ambiguity about whether this merely renders UI or actually initiates a verification request.

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 trigger: use this before create_business or request_payment, and names the concrete error signal (whatsapp_unverified) that should route the agent here. No when-not-to-use guidance is given, e.g. what to do if the person is already verified.

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