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

The description is rich ('sending nothing', 'no dm/reply means the comment would be left alone', 'AI mode calls the provider'), and the provider call does reconcile readOnlyHint=false. But the leading '[read]' tag plus a pure dry-run that 'sends nothing' directly conflicts with destructiveHint=true, leaving the agent with contradicting signals about whether the call is safe.

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?

Front-loaded with the operation class and dry-run semantics, then identifiers, then the return shape — a sensible ordering with no filler. The dense inline notation (platform=ig|fb|..., post_id=<platform>_post_id) is efficient but slightly slows parsing.

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?

No output schema exists, so the description supplies the return contract itself: {dm, reply, source: MATCH|AI|FALLBACK|null, error}, including how to interpret an empty dm/reply. Combined with the identifier conventions and the AI-provider side effect, an agent has everything needed to call it correctly.

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?

With 0% schema description coverage the description carries the whole load, and it does so well: it enumerates the platform values (ig|fb|tw|tt|yt|li|th), explains the composite `post_id` = `<platform>_post_id` (yt: `yt_video_id`), offers `post_uuid` as an alternative identifier, and defines `auto_reply` as the unsaved override sharing set_post_auto_reply's shape. Only `username` (one of six params) is left completely unexplained.

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: a dry-run evaluation of what the auto reply would answer to a comment `text` on a post, with 'sending nothing' bounding the scope. It is clearly distinguishable from set_post_auto_reply and get_post_auto_reply by the preview framing and the explicit reference to set_post_auto_reply's payload shape.

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?

Gives a concrete usage branch: 'Uses the stored settings, or the unsaved `auto_reply` ... when given', which tells the agent which inputs select which behavior. However, it never explicitly says to use this instead of set_post_auto_reply to preview changes, and gives no when-not guidance.

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