Mark messages

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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the mutation and idempotency profile is covered elsewhere. The description adds only the optionality of the two state axes and says nothing about permission requirements or what happens to messages not matched by the UIDs.

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?

A single front-loaded sentence with no waste; every clause (read/unread, flagged/unflagged) maps directly to a real behavior of the tool.

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 5 fully documented parameters, no nested objects, and no output schema to explain, the definition is nearly sufficient. The remaining gap is minimal: no indication of partial-failure behavior or confirmation of what is returned, though for an idempotent flag-setter this is minor.

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%, with each parameter (read, flagged, folder, account, uids) documented in the schema itself, so the baseline is 3. The description's only extra contribution is the "and/or" relationship between read and flagged.

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) and resource (messages) plus the two independent state axes (read/unread, flagged/unflagged), which clearly separates it from siblings like move and get_message. It lacks explicit sibling routing, but the operation is unambiguous.

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 "and/or" phrasing usefully implies that at least one of read/flagged should be supplied, but there is no explicit when-to-use guidance, no mention of alternatives, and no note about constraints such as the 500-UID batch cap or behavior when neither flag is provided.

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