ACTION_WAIT_CALL_ANSWER

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

With no annotations present, the description carries the full burden, and it does substantial work: it is blocking, it needs READ_PHONE_STATE, it returns early after 5 seconds if there is neither ringing nor OFFHOOK, and it names the two output variables (call_answered, call_error). The caveat that an outbound dial immediately reports OFFHOOK and therefore does not prove the other party answered is exactly the kind of behavior an agent cannot infer from the schema — though it also makes the tool's semantics for outbound calls ambiguous.

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 blocking behavior, permission requirement and outputs lead; the early-return caveat and the outbound-call caveat follow in descending importance. Every sentence adds information, and the only blemish is a stray doubled full stop, which does not impede comprehension.

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 no-output-schema tool with four optional parameters, the definition is nearly sufficient: outputs are named, the permission is named, and timeout behavior is described. The remaining gap is what happens when no call exists at all versus a call that never connects, which the 5-second rule only partly covers.

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%, so the parameters are documented and the baseline is 3. The description adds meaning beyond the schema by stating that string parameters support ${var} interpolation, which is not in the schema and matters because timeout_ms accepts strings and require/on_error are string variables. It also restates the timeout-to-call_answered=false mapping, which is complementary rather than redundant.

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 a specific verb+resource: it blocks and waits for a call to enter the OFFHOOK/in-call state, and it names the permission (READ_PHONE_STATE) and the output variables. It is clearly separable from a simple state read, but it never names the sibling tools it could be confused with (ACTION_GET_CALL_STATE, ACTION_WAIT_CALL_END), so it falls short of full sibling differentiation.

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?

Usage is implied by the word '阻塞等待': you would use this tool when you must wait until a call is actually answered, and the 5-second early return tells the caller it will not block for the full timeout when no call activity is happening. However, the description gives no explicit when-not guidance and never says to use ACTION_GET_CALL_STATE for a one-shot check or ACTION_WAIT_CALL_END for the opposite wait.

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