Chờ thư trong hộp

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

The description adds real behavior beyond the annotations: on a match it returns full content plus extracted_code, and on timeout it returns 204. That is exactly the kind of return/termination detail annotations (readOnlyHint, idempotentHint, openWorldHint, destructiveHint) cannot convey. It still omits whether the message is consumed/consumed-once and what polling/blocking behavior looks like.

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?

Two compact sentences that front-load the trigger condition and then the success/timeout outcomes, plus a short retry hint. The English half is somewhat redundant with the Vietnamese, which keeps it from a 5, but nothing 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?

With no output schema, the description usefully covers both return paths (matched payload incl. extracted_code, or 204 on timeout) and the retry strategy, which is the core of what an agent needs. Remaining gaps are the inbox_id parameter and whether the wait is blocking/polling, but the essential contract is present.

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 only 33% – just 'match' is documented in the schema. The description partially compensates by explaining match semantics (OTP or regex against content/subject/from) and by tying 'timeout' to a maximum wait in seconds, but inbox_id is never explained in either place. A 3 reflects partial compensation for a real coverage gap.

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 names a specific verb+resource ('chờ thư tới' / wait for a message to arrive in an inbox) and scopes it to OTP or pattern-matched mail, which clearly separates it from the passive read tools mail_inbox_messages and mail_inbox_message. It does not explicitly name those siblings as alternatives, so it stops short of a 5.

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 when to reach for this tool (waiting for an OTP or a message matching a pattern) and even gives a retry rule ('Gọi lại nếu cần chờ lâu hơn'). No when-not-to-use or explicit alternative is given, so it is clear context without exclusions.

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