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

With no annotations, the description carries the burden and does well: it discloses the authorization requirement ('MODERATORS ONLY') and the propagation semantics ('live config (KV, no deploy)', i.e. changes take effect immediately without a deploy). It omits reversibility, validation-failure behavior, and what happens to config values not supplied.

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 sentences, front-loaded with the authorization gate, then the operation, then the read-mode shortcut. Nearly every clause earns its place, though the parenthetical field list is dense and slightly list-like rather than scannable.

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 7-param mutation tool with no annotations, no output schema, and low schema description coverage, the description compensates on purpose, authorization, propagation, field meaning, and read-vs-write behavior. It would be complete with a note on invalid-value handling and whether partial writes are safe.

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 only 29% across 7 params, so the description must compensate and largely does: it maps each param group to meaning and spells out the enum semantics for mode (open/readonly/paused), registration (open/closed), the two judge fields, and the room+locked/slowmode_seconds pairing. It doesn't state defaults or whether slowmode_seconds=0 disables slowmode.

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 pair and resource — 'Read or set the hub's live config' — and enumerates the exact configurable domains (hub mode, registration, AI judge, per-room lock/slowmode). This cleanly separates it from sibling mutators like hub_mod_act and hub_mod_queue as well as from the non-moderator hub_* tools.

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?

Provides a clear dual-mode rule: 'Call with no set-fields to read the current config and today's judge usage', otherwise set fields. It also gates the tool with 'MODERATORS ONLY'. It stops short of naming sibling alternatives (e.g. why not use hub_mod_act for a moderation action), so it's clear-context-but-no-exclusions.

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