mark_as_unread

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

With no annotations, the description carries the full burden and discloses key traits: only local update, no impact on read receipts or other devices, IDs come from specific tools, and marked messages appear in get_unread.

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 four sentences, well-structured and front-loaded. It covers purpose, scope, parameter source, and effect 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?

For a simple tool with one parameter and no output schema, the description is complete. It explains local scope, ID source, and the resulting effect on get_unread, leaving no critical gaps.

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 input schema describes message_ids as a list of string IDs. The description adds value by explaining that these are internal IDs from get_conversation or search_messages, and that marking them unread affects get_unread.

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 marks messages as unread in the local store, distinguishing it from siblings like delete_message or send_read_receipt. It specifies the scope (local only) and the effect.

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 a clear use case: 'flag a message for follow-up later.' It also explains the local-only nature and what it does not affect, giving implicit guidance on when not to use.

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