Đọc thư trong hộp

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

The description discloses a real state mutation: the first read marks the message as seen. The annotations declare readOnlyHint=true and destructiveHint=false, i.e. no environment modification. Marking a message as read changes mailbox state, so the description directly contradicts the read-only annotation.

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 short sentences with the purpose and side effect front-loaded; no filler beyond the intentional Vietnamese/English duplication, which doubles length but keeps each sentence meaningful.

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 simple 2-parameter read tool with no output schema, purpose and side effect are covered, so an agent could call it. However, the unaddressed parameter semantics and the readOnly/idempotent mismatch leave meaningful gaps.

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?

Two required parameters (inbox_id, message_id) with 0% schema description coverage, and the description never mentions either parameter or their format. It must compensate for the coverage gap and does not, though the names are largely self-explanatory.

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+resource (read a full inbox message) and enumerates what is returned (content, headers, attachments), which distinguishes it from the list-style sibling mail_inbox_messages. It does not explicitly name the alternatives it differs from, but the 'full message' framing makes the scope unambiguous.

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 a clear use context ('before replying') and a trigger condition ('when you need the full content, headers and attachments'). There is no explicit when-not or named alternative, so it stops short of a 5.

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