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

Beyond the annotations it discloses real behavior: the ticket is short-lived, must be refreshed on each reconnect, and does not wake an idle AI chat. These add operational context the readOnlyHint/idempotentHint flags do not convey, and the "fresh tickets" note is consistent with idempotentHint=false.

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 tight sentences, front-loaded with the action and followed by the operational precondition. No filler, though the reconnect sentence and the idle-chat note could be merged without loss.

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?

An output schema exists, so return-value details are covered there, and the description supplies the lifespan and client precondition. Minor gap: it does not say where/how the ticket is consumed, but for a 1-required-param tool this is largely complete.

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 mailbox_id, account_id, and reason fully. The description adds no parameter-specific detail (e.g., how the ticket binds to mailbox vs. account), 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 (get) and a distinct resource (a short-lived WebSocket ticket) for this mailbox, which no sibling tool covers. It is easy to tell apart from the read/list/update email tools, though it never names a sibling to route against.

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?

"A running client must connect and reconnect using fresh tickets" and "This does not wake an idle AI chat" imply the precondition (a live client) and an implicit when-not (idle subscriptions), but no alternative tool or explicit negative routing is given.

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