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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=true), and the description goes well beyond them by disclosing the propose-then-confirm protocol: status='confirmation_required', an action_id and plan_token, and that the write only lands after confirm_action. That is exactly the kind of multi-step consequence an agent cannot infer from structured fields.

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?

Front-loaded with the core action, then the id-sourcing rule, then the confirmation protocol — a sensible order with no filler. The confirmation sentence is dense (status, action_id, plan_token, confirm_action) but each element is operationally necessary, so it earns its length.

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 destructive two-parameter mutation with no output schema, the definition covers what it does, how to source the id, what it does not do (mark read on fetch), and the full confirmation handshake. Nothing an agent needs to invoke 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 coverage is only 50% — flag has an enum and description, but message_id is bare. The description compensates by specifying the id's provenance (mail_list_messages) and that the folder is read off the stored message, which is non-obvious context the schema does not carry. It does not add format detail for the integer-or-string id, so not quite a 5.

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 ('Mark ONE of the caller's messages read or unread, starred or unstarred') and bounds scope to a single message. It is clearly distinguishable from mail_get_message and mail_list_messages, which are both named.

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?

Explicitly tells the agent where the message_id comes from (mail_list_messages) and that the folder is derived from the stored message rather than guessed. It also pre-empts a likely wrong assumption: reading via mail_get_message does not mark a message read, so this is the only path that does.

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