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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), so the bar is lower. The description still adds genuine behavioral detail beyond them: the change is a *shared* read receipt (affects other users' visibility) and it creates no version, which tells the agent this is a lightweight, non-versioned mutation. It stops short of describing auth requirements or response shape.

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?

Two tight sentences, front-loaded with the action and followed by the boundary constraint. Every clause earns its place with no 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?

With a full-coverage input schema, an output schema, and non-trivial annotations, the description supplies the one thing structured fields cannot: that this mutates a shared read receipt without versioning. Adequate for a simple toggle; only explicit sibling routing or permission notes are 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%, including the rich 'reason' guidance, so parameter meaning is fully carried by the schema. The description adds no parameter-level detail (no clarification of read semantics or account_id scoping), so the baseline 3 applies.

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?

States a specific verb ('Mark ... read or unread') and a precise resource scope ('a received email'), and further bounds it by saying it does not edit content or create a version. An agent can distinguish this from mailbox_email_get, mailbox_email_list, and mailbox_update without opening any schema.

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 implies the use case (toggling read state on a received email) and implicitly excludes content edits, but it names no alternative tool and gives no explicit when/when-not conditions intro. Usage is inferable but not spelled out.

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