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

Annotations only give the flags; the description goes further by disclosing that the hangup is immediate and bilateral, that the call is left untouched if already ended (with hung_up false), and that summary/transcript/recording still arrive afterward. This is exactly the idempotency and side-effect detail an agent needs and is consistent with the idempotentHint/destructiveHint annotations.

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?

Three tight sentences with the effect (immediate bilateral hangup) front-loaded, followed by the post-call artifact note and the no-op guard. No filler or repetition.

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 the description still supplies the key behavioral nuance (idempotent no-op, artifacts follow). Nothing an agent needs to invoke this correctly is missing.

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% with a single documented parameter, so the schema already carries the semantics. The description mentions where call_ref comes from (wa_ai_call_start or wa_ai_list_calls) but that is largely echoed in the schema text, adding little beyond the baseline.

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?

Specific verb ('End/hang up') plus resource ('a live AI voice-agent call') with explicit scope: calls started via wa_ai_call_start or inbound calls an agent answered. An agent can distinguish this from wa_ai_call_start and wa_ai_call_get without opening a 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?

Clear context for when this applies (a live call, whether outbound or inbound-answered) and states the already-ended case is a no-op. It does not name a sibling alternative or an explicit when-not, but the triggering condition is unambiguous.

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