Read one message

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

Annotations only hint at mutation via readOnlyHint=false; the description supplies the concrete side effect ('Marks the message as read'), which is exactly the kind of behavior an agent needs before calling. It does not cover failure modes or whether re-reading re-marks an already-read message, but idempotentHint=true already addresses the latter.

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 clauses, front-loaded with the action and its return payload, then the side effect. No filler and nothing redundant with the schema or annotations.

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 an output schema present, return values need not be explained, and annotations cover safety/idempotency; the description's coverage of the read-marking side effect closes the main gap. Minor omissions (behavior when the message id is invalid) are acceptable for a simple read tool.

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%, so the schema already documents email, message_id and the max_chars truncation bound. The description adds no parameter-level detail beyond what the schema provides, making the baseline 3 correct.

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+resource ('Read one message') and goes further by naming what is extracted from the body: text, `otp`, `codes`, `links`. It is clearly distinguishable from list_messages by the singular scope, though it never names the sibling 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?

No explicit when-to-use or when-not-to-use guidance; the workflow is only implied (read a single message obtained from list_messages, per the schema note on message_id). No mention of how this relates to wait_for_message for a not-yet-arrived message.

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