set_watched_mailboxes

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

With no annotations, the description carries the full behavioral burden, and it does so concretely: add_exclude excludes folders from scanning for '노이즈/대용량 폴더 등', remove_exclude restores '기존 제외 폴더', and reset_exclude initializes to '시스템 기본값'. It also discloses that folder discovery is automatic. Gaps remain for edge cases like combining reset_exclude with add/remove or invalid folder names, but the core side effects are clearly stated.

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 description is compact and front-loaded: one sentence stating the purpose, three terse parameter definitions, a lookup instruction, and a concrete example. It contains no filler; each clause carries operational information and the flow from purpose to parameters to example is natural.

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 mutating configuration tool with no annotations and no output schema, the description covers the essential invocation context: target account, the three operations, folder-name source and case sensitivity, and an example. It omits success/error response behavior and interaction between operations, but such details are not necessary to make a correct call for the common cases.

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?

The schema already documents all four parameters (100% coverage), so the baseline is 3. The description adds real value beyond the schema: it explains that add_exclude targets noise/large folders, remove_exclude restores previously excluded folders, reset_exclude reverts to system defaults, and it adds the exact-case requirement for folder names ('대소문자 정확히') plus a concrete example mapping account_label:'다음개인' to add_exclude:['카페편지함'].

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 opens with a precise statement: '계정의 폴더 제외 목록을 관리합니다' (manages the account's folder exclusion list) and immediately distinguishes this from automatic folder discovery: '폴더 발견은 자동이며, 여기서는 제외 목록만 관리합니다.' It enumerates the three concrete operations (add_exclude, remove_exclude, reset_exclude), making the tool's resource and actions unmistakable and separating it from siblings like list_mailboxes or get_watched_mailboxes.

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?

The description provides clear context: this tool is for exclusion-list management only, not for discovery ('폴더 발견은 자동이며'), and it instructs the agent to verify folder names against 'list_mailboxes의 currentImap 목록' with exact case ('대소문자 정확히'). However, it does not explicitly reference get_watched_mailboxes as the tool for viewing current exclusions, so the when-to-read vs when-to-write distinction is left somewhat implicit.

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