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

Annotations already indicate this is a mutation (readOnlyHint=false), but the description adds crucial behavioral context beyond that: IMAP IDs encode folder+UID and change on moves/draft updates, so the caller must always reuse the last-operation ID. It also explicitly forbids passing RFC Message-ID, subject, or pre-move IDs. This is valuable, non-obvious behavioral information.

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 front-loaded with purpose and a prerequisite, then presents essential ID-resolution rules. It is longer than strictly necessary because it duplicates the schema's parameter text, but every included caveat ('CHANGES when moved', 'Never pass: RFC Message-ID') carries real operational value.

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 state-change tool with no output schema, this description covers the only genuinely difficult part: how to obtain a valid email_id, under what conditions it goes stale, and which ID forms must never be used. The optional account_id handling is fully specified in the schema. Nothing needed for a correct invocation is missing.

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%, and the property descriptions already fully explain email_id and account_id. The tool description repeats the email_id semantics rather than adding new parameter-level meaning, so a baseline score of 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 opens with a specific action ('Mark one exact email unread') and clearly identifies the resource ('one exact email') and the intended state ('unread'). The word 'exact' and the instruction to 'Resolve email_id first' distinguish this from bulk operations and from the sibling email_mark_read without ambiguity.

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 clearly establishes when to use the tool: after resolving an email_id via email_list_messages or email_list_folder_messages, and it warns against using stale or non-provider IDs. It does not explicitly name the alternative email_mark_read or state 'when not to use' conditions, but the workflow context is sufficiently clear.

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