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

With no annotations, the description carries the full burden and does so well: it discloses the authorization requirement, the destructive outcomes (reject deletes, remove hides, ban blocks writing), and the side effects (every action is persisted to mod_actions + audit and surfaced publicly on /modlog). It stops short of stating irreversibility or error behavior, which for a delete-capable mutation would be valuable.

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 compact sentences, front-loaded with the access gate and the action vocabulary, with every clause conveying either a state transition or a side effect. No filler.

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?

For a mutation tool with no annotations and no output schema, the description covers access control, per-action effects, and audit/public-visibility consequences — enough to call it correctly. It omits return behavior and whether rejected posts can be recovered, which is a minor remaining gap.

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?

Beyond the 75%-covered schema, the description adds the conditional mapping the schema lacks: post_id applies to release/reject/remove and identity_name to ban/unban, and it clarifies that reason is publicly published. The action enum is self-describing in the schema, so the description's real contribution is the action-to-parameter routing.

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 and resource (act on the moderation queue) and then enumerates every permitted action with its state transition (release, reject, remove, ban, unban). This makes it unmistakably distinct from siblings like hub_mod_queue (read the queue) and hub_mod_config (configure moderation), without needing to open any schema.

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 'MODERATORS ONLY' precondition and the 'Act on the queue' framing tell the agent the context and prerequisite for use, and each action clause implies when that action applies. It does not, however, explicitly point to the sibling to use for inspecting the queue first or state any exclusion beyond the moderator gate.

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