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

The description adds genuinely useful behavior — no message is sent, return shape is {answer, source: MATCH|AI|FALLBACK|null, error}, null means silence, and AI mode makes an external provider call. But it labels the tool "[read]" while annotations declare readOnlyHint=false and destructiveHint=true, a direct conflict on the tool's safety profile that will confuse an agent deciding whether to call it.

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 dense sentences with the read/dry-run framing front-loaded, then parameters, then return contract. Nothing is redundant, and the platform enum and return shape are both load-bearing since there is no output schema.

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 supplies the return value semantics (including the null/error cases) that would otherwise be missing, and covers the optional-parameter fallback behavior. What remains unaddressed is the authorization/scope needed for the account and the cost implication of the provider call in AI mode.

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 coverage is 0%, so the description carries the load and does so well: it supplies the `platform` enum values (ig|wp|fb|tw|tg) that the schema omits, explains that `text` is the inbound message, and specifies that `auto_reply` mirrors the `set_account_auto_reply` shape with stored settings as the fallback. Only `account_id` goes unexplained, which is self-evident.

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 action and resource: a dry run of the account's message auto reply against an incoming `text`, with the explicit guarantee that nothing is sent. It also anchors itself against siblings by referencing `set_account_auto_reply`'s shape, so an agent can separate this preview from the get/set pair.

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?

Explains the two operating modes clearly: use stored settings by default, or pass an unsaved `auto_reply` payload to preview an uncommitted configuration. It stops short of naming `get_account_auto_reply`/`set_account_auto_reply` as explicit alternatives, so the when-not-to-use routing is only implied.

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