batch_mark_unread

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

No annotations are present, so the description carries the entire burden of disclosing behavior. It only states the action without mentioning side effects, permissions, or reversibility. For a batch mutation, it does not clarify whether existing read flags are overridden or simply set to unread, nor does it note any limits or consequences. This leaves the agent uninformed about the operation's impact.

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 a single concise sentence with no unnecessary words. It front-loads the core action and meets the standard for efficiency. While it may be too brief for full clarity, it is not verbose or repetitive.

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?

Given the tool has two parameters (one required, one optional) and no output schema, the description is insufficient for correct invocation. It does not explain the purpose of 'mailbox', any constraints on 'message_ids' (e.g., length, format), or what the tool returns or affects. The minimal description leaves significant gaps that an agent needs to fill through inference.

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%, and the description offers no explanation of the parameters. The schema shows a required 'message_ids' array and an optional 'mailbox', but the description does not clarify what 'mailbox' represents or how the IDs are used. The agent must work with raw schema fields without any added meaning.

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 action: 'Mark a list of messages as unread.' It specifies the verb (mark), resource (messages), and the word 'list' implies batch operation, distinguishing it from the singular 'mark_unread' sibling. However, it does not explicitly differentiate from other batches like 'batch_mark_read' beyond the unread direction.

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 no guidance on when to use this tool versus alternatives such as 'mark_unread' for single messages or 'batch_mark_read' for the opposite operation. It does not mention any context, prerequisites, or conditions that should trigger this tool. The agent must infer usage solely from the name and sibling list.

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