triage_digest

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

Beyond the readOnlyHint annotation, the description discloses sampling behavior (up to `max` matches, hasMore flag), clarifies that byAge uses thread's first message date, and states 'SIDE EFFECTS: none'. These details help the agent anticipate tool behavior and limits.

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 well-structured with bolded USE WHEN/DO NOT USE and a final SIDE EFFECTS note. It front-loads the core value proposition and every sentence adds necessary context without redundancy.

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?

The tool is well-covered: purpose, usage guidance, side effects, and sampling behavior are explained, and an output schema exists for return values. However, missing parameter semantics for `topN` and `query` prevent a perfect score, as the agent cannot fully understand how to configure the digest.

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%, so the description must compensate for parameter meaning. It only explains `max` as the sampling limit. `topN` and `query` are left undefined, leaving the agent to guess their roles. This is a significant gap for parameter understanding.

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 clearly states the tool provides a structured mailbox overview for triage decisions, listing specific outputs (sender, label, age buckets, unread/attachment counts). It explicitly contrasts with a raw thread list and distinguishes from sibling tools like search/get_thread.

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?

Explicit USE WHEN and DO NOT USE sections give concrete scenarios (bulk-archive/snooze/label, summarizing inbox state) and direct users to search/get_thread for reading specific threads. This leaves no ambiguity about when the tool should be selected.

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