Liệt kê email gần đây

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

Beyond readOnlyHint/openWorldHint, the description discloses two behaviors the annotations cannot express: fetching does not flip the read flag on the server, and results carry an ad-suspicion flag from rule G01. It omits auth requirements and any rate/volume limits, but the non-mutating IMAP semantics and output enrichment are genuinely useful additions.

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?

A single compact sentence with the core purpose front-loaded and no filler. The trailing reference to 'luật G01' is cryptic without context, which costs a point but does flag that output includes an ad heuristic.

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?

An output schema exists, so return values need no explanation, and the read-only safety profile is covered by annotations. Still, for a 4-parameter tool with zero schema description coverage and near-identical siblings, the definition leaves folder selection, result capping, and tool selection under-specified.

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 0% – limit, folder, since_days, and unread_only have only titles and defaults, with no notes on accepted values or effect. The description compensates only vaguely, hinting at recency ('gần đây') which loosely maps to since_days, and does nothing for folder scoping or the distinction between unread_only filtering and the stated non-marking behavior, which is an easy source of agent error.

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 and resource ('Liệt kê email gần đây'), adds ordering ('mới nhất trước'), transport ('qua IMAP'), and a key side-effect guarantee ('không đánh dấu đã đọc'). What it lacks is any differentiation from close siblings like mail_read or email_check, so the agent cannot fully disambiguate from the text alone.

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 phrase 'email gần đây' – this is the listing entry point rather than a single-message reader. However, there is no explicit when-to-use or when-not-to-use statement, and no mention of siblings such as mail_read, so the agent must infer the boundary itself.

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