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

Annotations already declare readOnly, idempotent and closed-world, yet the description still adds real behavioral depth: it explains that stale complete snapshots can be returned, that `not_cached`/`incomplete` are not proof of absence, and that `checkpoint.complete` measures account-wide folder watermark coverage separately from thread completeness. That is exactly the kind of non-obvious semantics an agent needs before acting on a cached result.

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?

The cache-only guarantee is front-loaded and every sentence carries a distinct operational caveat. It is dense and leans on bare output field names without introduction, which makes it slightly harder to parse than it needs to be.

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, the description takes on the return-value burden and does so well for the key status, staleness and checkpoint fields, including the warning to inspect `checkpoint.gaps` and freshness before CRM use. The remaining gap is input-side: nothing tells the agent where `accountId` and `threadId` come from.

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 0%, so the description must carry the parameter burden, yet neither `accountId` nor `threadId` is mentioned — no ID format, no source for obtaining the IDs, no note that both are required. The names are self-explanatory but that is all the agent gets.

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 opening clause states a specific verb and resource (read the durable mailbox cache) and immediately scopes it with 'never calls IMAP or another provider', which distinguishes it from the live-fetch siblings like get_thread. It stops short of naming those siblings explicitly, so the differentiation is implied rather than stated.

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?

The 'cache-only, no provider call' framing implies this is the cheap read path versus get_thread or request_cached_thread_refresh, and the caveats about `not_cached`/`incomplete` hint at when results should not be trusted. However, there is no explicit when-to-use/when-not-to-use statement and no named alternative for getting fresh data.

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