Get Mailbox Changes

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered and the description only needs to add sync semantics, which it does by framing calls as cursor-based resumption. It does not disclose whether the response includes a new cursor, how the per-type cursors interact, or what happens on an expired/ancient cursor.

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 sentences, with the positive use case front-loaded and the exclusion following immediately. Nothing is wasted or buried.

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 and annotations covering safety, the description supplies the essential sync framing plus a boundary against search use. Its residual gap is the semantics of the seven cursor/type parameters in combination, which a ten-parameter sync tool arguably should address.

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 every one of the ten parameters is already documented, establishing a baseline of 3. The description adds no meaning beyond the schema about the per-type cursor parameters or how they relate to the 'types' filter — for example whether a cursor is only honored when its type is listed.

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?

The description states a specific action and resource: resuming mailbox sync from a prior state cursor, which is clearly distinct from a one-off read. It does not spell out that the result is a set of change records across the message/folder/thread/identity/etc. types, so the name and schema still carry some of the meaning.

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?

It gives an explicit exclusion — not for ad hoc message search — which steers an agent toward the search/list siblings. It does not name the alternative tool or state the prerequisite that a valid cursor from a previous response is required.

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