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

Discloses the non-obvious side effect that reading marks messages as read, which is essential context and consistent with readOnlyHint=false. It also adds ordering and thread-grouping behavior that annotations do not carry. No auth, rate-limit, or pagination context, so it falls short of a 5.

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 plus a reference link, with the default behavior and side effect front-loaded ahead of the optional parameter modes. No filler.

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 no output schema, the description adequately conveys the return shape (unread, oldest first, thread-grouped) and the mutation side effect, plus a docs link for depth. Minor gaps remain on what a response payload actually contains, but nothing an agent needs to call it correctly 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 0%, so the description carries the burden and does it: thread_id is explained as fetching a thread's full history rather than just unread, and include_read expands scope to read messages. Both params are covered, though no accepted-value or UUID format hints beyond the schema.

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 and resource plus the default scope: 'Returns unread messages addressed to you'. Ordering ('oldest first'), grouping ('grouped by thread'), and the side effect ('marks them read') are all named, so an agent can distinguish this from list_threads or send_message without opening a 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?

Gives conditional guidance for the two modes ('Pass thread_id for a thread's full history, or include_read...'), which is genuinely useful. However, it never states when to reach for this tool instead of siblings like list_threads or ask_human, so usage is implied rather than framed against alternatives.

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