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

Annotations only declare the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=false); the description adds real behavior beyond that — the 8-character code return, that it is typed into the same phone, and the mutual-exclusivity constraint against the QR and restart tools. It does not cover code lifetime/expiry or what happens on an invalid number, which is the remaining gap for a session-mutating tool.

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 core action and return value are front-loaded, and the constraints follow in a clear sentence with an explicit rule ("Use only ONE pairing method at a time"). Slight redundancy in explaining "the phone with their WhatsApp" twice, but no sentence is wasted.

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 one-parameter tool with no output schema, the description is nearly sufficient: it explains the returned code, where it is entered, and how it conflicts with sibling tools. The missing pieces are phone-number formatting and error/timeout behavior, which an agent would need 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 0% for the single required parameter, and the description never mentions phone_number or its expected format (country code, E.164, digits only). With the schema providing no help, the description should have compensated and does not.

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?

"Initiates pairing and returns an 8-character code to enter in WhatsApp" gives a specific verb, resource, and return artifact, and immediately distinguishes the tool from its sibling get_pairing_qr by naming the QR-code alternative. An agent can tell the two pairing methods apart without opening either schema.

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 states the exact selecting condition (user has only one phone, same phone that holds WhatsApp) and an explicit exclusion set: never call request_pairing_code with get_pairing_qr, and never call restart_session while pairing. Both the when-to-use and the when-not-to-use cases are spelled out.

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