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

Annotations already signal idempotency and non-destructive mutation, and the description adds login requirements, batch semantics, and the non-obvious partial-failure behavior where unknown ids land in failed[] without failing the whole batch.

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?

Three short labeled sections cover login/batch, the combination chain, and pitfalls. There is no filler, and the most decision-relevant information is front-loaded.

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 one-parameter mutation with strong annotations, the description covers the full workflow, failure semantics, and idempotency. Even without an output schema, the failed[] disclosure gives an agent enough to handle the result 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 coverage is 100%, and the schema already documents deliveryIds as list_my_organization_notifications items[].id with a max of 100. The description reinforces this but adds no new parameter meaning beyond the structured field.

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 states the exact operation with a concrete verb and resource: '把组织通知标为已读', plus batch behavior. It is clearly distinct from sibling mark_conversation_read and is tied to list_my_organization_notifications as its data source.

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?

It gives an explicit workflow: get ids from list_my_organization_notifications, read them to the user, then pass all deliveryIds to this tool. It does not explicitly name excluded alternatives, but the resource scope makes when-to-use unambiguous.

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