watch_property

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

With no annotations, the description carries full behavioral burden and does so thoroughly. It discloses interval clamping/defaulting, per-pass cost, object revalidation with IsValid(), resumed/lost event behavior, baseline resets, and that only stop_stream ends a watch. This goes far beyond what a typical description provides.

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 description is long but each sentence carries substantive information, from purpose to parameters to event semantics to lifecycle. It is front-loaded with the core purpose and read-only note, then organized by parameter and behavior. No filler or tautology is present.

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 tool with 5 parameters, no annotations, and no output schema, this description is remarkably complete. It covers what the tool does, how parameters behave, performance implications, event semantics, lifecycle, and how to retrieve results via poll_events. An agent has enough context to invoke and manage the watch 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?

Schema description coverage is 0%, so the description must compensate, and it does. It explains names (one name or list), every (records every sample vs. changes only), interval_ms (clamped, default, performance guidance), label (unique, reuse raises), and ref implicitly through examples like 'first:PlayerController' and reference-following behavior. All five parameters are meaningfully described.

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?

The description opens with a specific verb and resource: 'Sample properties on a timer and record an event whenever a value changes.' It also labels the operation as read-only, which clearly distinguishes it from mutation tools and frames its streaming nature. It is immediately distinguishable from siblings like get_property, poll_events, and stop_stream.

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 description gives practical guidance on when and how to use the tool: read results with poll_events, nothing is pushed, stop with stop_stream, and labels are unique. It also advises keeping watches few and slow due to game-thread cost. It does not explicitly contrast with one-shot alternatives like get_property, but the usage context is clear enough.

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