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

Adds substantial context beyond annotations: login requirement, 30-day window, and the crucial distinction that 'seen' means Agent-seen rather than App-read. It also states that markSeen defaults to false, which matters for repeated calls and avoids accidental read-state changes.

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: login requirement, time window, sibling alternative, type usage, and seen/markSeen semantics all appear without filler. Each clause carries useful information.

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?

Covers the main invocation concerns: auth, window, return data containing object ids, type categories, and marking behavior. It lacks some return-shape detail and does not disambiguate against list_my_organization_notifications, but it is sufficient to call the tool correctly.

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 100%, so the schema already defines limit, markSeen, and unseenOnly. The description still adds meaning by clarifying that unseenOnly filters Agent-unseen items and that markSeen only affects the current batch, though it adds nothing about limit.

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?

Starts with a clear action and resource (推送收件箱) and states the 30-day scope plus login requirement. It explicitly distinguishes private messages by naming list_my_conversations as the sibling to use instead.

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 an explicit alternative for private messages (list_my_conversations) and explains that the inbox is queried by type for invitations/cooperation requests. It does not address other related notification tools such as list_my_organization_notifications, so guidance is clear but not exhaustive.

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