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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds two pieces of context not in the structured fields: the login requirement (【需要登录】) and the exact side effect (updating lastReadAt). It does not discuss error cases or rate limits, but the added specifics are genuinely useful.

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?

One tight sentence that front-loads the login prerequisite and the action, with zero filler. Every clause earns its place.

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 single-parameter mutation with no output schema, the description covers what it does, the auth requirement, and the side effect. It is essentially complete, with only minor room for noting idempotency or unread-state edge 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?

Schema coverage is 100% with a single documented required parameter (conversationId), so the schema already carries the parameter meaning. The description adds nothing about the id format or constraints, which is acceptable given full schema coverage.

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 and resource ('把某个会话标记为已读' / mark a conversation as read) and even names the field affected (lastReadAt), which is more precise than the name alone. It is distinguishable from the notification variant (mark_organization_notification_read) by resource, though it does not explicitly call that out.

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 intent is implied by the action itself — use it to clear unread state on a conversation. There is no explicit when-to-use guidance, no mention of how it relates to read_messages or get_conversation, and no exclusions.

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