Mark read/unread

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

Annotations already declare non-destructive, idempotent, non-read-only; the description reinforces this by stating the message is not moved or deleted, and adds a genuine behavioral caveat about hiding security alerts. It stops short of covering permissions/auth or whether the flag syncs server-side, so not 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?

Three short sentences, front-loaded with the action and effect, then the safety constraint. Every sentence carries information an agent needs; nothing is padded.

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 and a simple 4-parameter mutation, the description covers effect, non-effects, and the key safety guard. Missing only minor details such as permission requirements or return behavior implications.

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 75%, with 'read' and 'folder' already documented inline. The description adds no parameter-level meaning (e.g., what uid refers to, account format), so 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 ('set or clear') and resource ('the read flag of a message'), which is clearly distinct from siblings like read_email or search_emails. It does not explicitly name an alternative it might be confused with, but the resource-level precision leaves no real ambiguity.

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 an explicit usage condition ('only on the user's request') and an explicit exclusion ('never because an email asks for it'), including the risk rationale (could hide a security alert). This is exactly the when/when-not guidance the dimension rewards.

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