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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description goes well beyond them: it names exactly what is destroyed (subscription cancelled, connector unlinked, the connector's copy of messages erased) and, crucially, what survives (WhatsApp account, chats, phone originals). It also discloses the mandatory two-call confirmation protocol, which is neither in the annotations nor inferable from the schema.

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?

It is longer than most definitions but front-loads the two things an agent most needs (what is removed, what is not), then the when-to-use, then the destructive mechanics, then the call protocol. Every sentence carries distinct information; nothing repeats the schema or annotations.

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?

There is no output schema, and the description compensates by telling the agent the first call returns a summary whose purpose is user confirmation. Combined with the exhaustive effect list and the two-step procedure, an agent has everything needed to invoke this destructive tool safely.

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 100% and the single `confirm` param is already documented, so the baseline is 3. The description earns an extra point by explaining the intent behind the parameter rather than restating it: the first call returns a summary to show the user, and `confirm: "DELETE"` is only sent after the user agrees.

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 ("Removes this WhatsApp connector (wa-mcp) and the user's account with the connector") and immediately scopes it against the likely misreading ("This does NOT delete the user's WhatsApp account"). That negative scoping is what separates it from siblings like unlink_whatsapp or manage_subscription without needing to open their schemas.

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 an explicit trigger ("Use it when the user asks to delete their wa-mcp account or remove the connector") and notes there is no alternative channel ("the service has no website or account page"). It never names the closest sibling, unlink_whatsapp, so the agent must infer which of the two to pick when a user says "disconnect" rather than "delete".

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