Monitor a LuaStateProxy's generic cross-state Event

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is known. The description still adds material context beyond them: the specific side effect ("changes persistent executor-side observer or hook state"), the buffer bound, and the confirm=true requirement for start/stop. It stops short of describing failure/partial-write behavior, so 4 rather than 5.

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 critical fact is front-loaded, but the body is a telegraphic metadata dump where several clauses duplicate structured data ("idempotency=contextual-write" vs idempotentHint=false, the full signature vs the schema, "Phase: act; cost=medium"). It is compact but not every line earns its place.

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 8 parameters, one required, no output schema, and annotations present, the description covers most of what an agent needs: the lifecycle, buffer bounds, the confirm gate, the mutated state, and a suggested verification step (assert-state). It omits return/poll-result shape and what happens on the read path, leaving a small 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?

Schema description coverage is 100%, so the baseline is 3. The description's inline signature restates the fields already in the schema and adds only two semantic points: polling is by key and confirm must be true for start/stop. Undocumented-in-prose parameters like clear and limit gain nothing, so no lift above baseline.

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?

Opens with a specific verb and effect ("WRITES LIVE GAME STATE when starting/stopping") and names the exact resource (LuaStateProxy.Event), plus the retention model (bounded 200-event buffer polled by key). It does not name its near-identical siblings (actor-event-monitor, comm-channel-monitor, watch-value), so an agent must infer differentiation itself, keeping it below 5.

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 action lifecycle (start/poll/stop) and the confirm=true gate imply how to use the tool, and "Requires: active-client, explicit-mutation-approval" gives a precondition. However, it never states when to choose this over actor-event-monitor or comm-channel-monitor, so the when/when-not guidance is only implied.

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