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

No annotations, so the description carries full burden and does disclose two important behaviors: authentication requirement (connector OAuth or private Bearer) and the non-obvious fact that the server persists no read flags, making read state caller-owned. Return shape for the list path and pagination behavior are still unstated.

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?

Four tight sentences, front-loaded with the primary purpose, then mark_read semantics, then the cursor-persistence workflow, then auth. Every sentence adds information with no redundancy.

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 annotations and no output schema, the description covers purpose, auth, state model, and cursor reuse — enough to call the tool correctly. It stops short of describing the listed message payload or what happens when limit is hit.

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 only 25%, so the description must compensate; it meaningfully explains 'after' (reuse the returned readCursor), 'through' (last read seq, mark_read only), and the action enum. Limit's role as page size is left implicit.

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 ('List your own messages') and covers the dual-mode action (list vs mark_read) clearly. The contrast with sibling agent_send_message is implicit via 'inbox', but no sibling is named explicitly.

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 explicit conditional routing: 'To acknowledge reading, action=mark_read', plus a concrete workflow ('Save readCursor and use it as after next time'). Strong on when-to-use for the mutation path, though it never names an alternative tool (e.g. agent_send_message) to route away from.

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