mark_read

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

Annotations already declare destructiveHint=true and non-idempotent behavior; the description adds genuinely new context by disclosing the required 'allow_manage' local setting and the fact that the change is verified. It does not, however, explain what happens on a conflict or how the verification result is surfaced.

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 short sentences, no filler, with the core action and the prerequisite permission front-loaded in that order. Every clause carries information.

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 mutation tool the annotations cover the safety profile and the description covers the auth prerequisite, which is good. But with a 0%-coverage schema and no output schema, the description leaves the caller guessing about identifier semantics and what the promised verification returns.

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% across four parameters. The phrase 'read/unread state' maps loosely to the boolean 'read' parameter but never says that the default true marks as read, and mailbox, account_id, and message_id receive no explanation at all despite being required or defaulted.

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: it changes read/unread state and verifies the result. This clearly separates it from read_message and search_messages, which retrieve rather than mutate state. It is not a tautology of the name, though the name 'mark_read' understates the bidirectional read/unread capability the description reveals.

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 word 'Explicitly' hints that this is for deliberate state changes rather than incidental ones, and the permission prerequisite is stated. However, no alternatives are named and there is no guidance on when the caller should use this versus simply reading a message or relying on implicit read marking.

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