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

Annotations already disclose the safety profile: readOnlyHint=false, destructiveHint=false, and idempotentHint=true, all consistent with a non-destructive state-change operation. The description adds value by clarifying the subtle batch behavior (a single operation over the whole set) and the deliberate-act nature of marking, which is useful context beyond the annotations. No behavioral claims are made beyond what the annotations support.

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 terse sentences, each earning its place: the first states the core action, the second disambiguates from the read_email sibling, and the third delivers the critical batching instruction. The purpose is front-loaded in the opening words, and there is zero filler or repetition of schema content.

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 two-parameter mutation tool with full schema coverage and annotations carrying the safety profile, the description is nearly complete: an agent knows what the tool does, what to pass, and how to batch. The only notable absence is any mention of the return value or response behavior, and since no output schema exists, a brief note about what the call returns would have made this fully self-sufficient.

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 documents both parameters thoroughly. The uids schema description is especially detailed, covering source (list_emails or search_emails), batching rationale, the 500-item cap, and the one-element-array case, while the mailbox default is also stated. The tool description's final sentence reinforces the batching guidance but adds nothing beyond what the schema already conveys, so baseline 3 is appropriate.

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 uses a specific verb+resource ('Mark messages as read') and is unambiguous about the state change being performed. The sentence 'Reading a message does not mark it read - this is the deliberate act that does' implicitly distinguishes this from the sibling read_email, though it never names the sibling explicitly. Purpose is clear, but sibling differentiation is inferred rather than stated outright.

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 gives clear operational context: 'Pass every message you want marked in one call' tells the agent how to batch its invocations efficiently. However, it does not explicitly name alternatives like read_email (fetch content without state change) or mark_unread, nor does it state when not to use this tool. The read-versus-mark clarification is a semantic distinction, not a routing rule, so guidance on choosing between siblings is only implied.

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