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

Annotations only give generic readOnly=false/destructive=true/openWorld=true; the description adds substantial specifics beyond them: confirmation gating via confirmed=true, idempotencyKey reuse rules, no API keys in chat, incomplete local history, untrusted message data, no automatic resend, and the two distinct consent scopes required. This is the kind of operational detail the annotations cannot convey.

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 dense paragraph, but front-loaded with purpose then actions, and every sentence carries operational weight (QR refresh, idempotency, consent scopes, untrusted data). No filler, though the density makes it slightly harder to scan per-action.

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 seven-action destructive connector with an output schema (return values need not be explained), the description covers the risky flows well: connect/QR, confirmation, idempotent sends, and consent. It stops short of mapping parameters to individual actions and omits pagination behavior, which an agent invoking read_messages would benefit from.

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 0%, so the description must carry the burden. It adds real meaning for confirmed (set only after confirming exact group/message), idempotencyKey (reuse it and the exact input on retry), and groupJid (resolve the exact JID before reads/sends), but says nothing about limit, cursor, text, or which parameters apply to which action. Coverage is partial against a 7-parameter surface.

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 opens with a specific verb and resource ('Use your organization's own WhatsApp linked-device account for group messaging') and enumerates the seven actions. It explicitly distinguishes itself from sibling Business API tools ('Existing Business API WhatsApp tools remain separate'), which is exactly what an agent needs to choose between this and send_whatsapp_message.

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?

Gives explicit when/when-not and sequencing: 'Connect, then call qr and show the returned QR image', 'refresh qr after expiry', 'List groups to resolve the exact groupJid before reads/sends', and 'If send outcome is unknown, read the group and never automatically resend.' It names prerequisites (fresh whatsapp_groups:read consent) and the alternative path (Business API tools remain separate).

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