Watch a property change over time

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

Beyond the readOnly/idempotent annotations, it discloses the critical non-obvious trait that the call blocks for roughly durationMs and is inherently synchronous, plus prerequisites (active-client, resolved-target), cost class, and the exact return shape. That is exactly the behavioral context annotations cannot carry.

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?

It is well front-loaded, but the trailing metadata block ('Phase: observe; cost=medium; idempotency=read-only... Safety: read-only... On failure: inspect tool-schema') largely duplicates the annotations (readOnlyHint, idempotentHint) and the schema signature, padding the text without adding selection or invocation value.

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 no output schema, the description correctly supplies the return shape ({ Path, Property, Samples, changeCount }) and the sampling semantics, so an agent knows what it will get back. It is nearly complete; the only gap is behavior on error (missing instance/property) beyond the generic 'inspect tool-schema' pointer.

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% and each parameter already documents defaults, ranges and semantics, so the baseline is 3. The description restates the signature and repeats the blocking/duration guidance that the schema's durationMs description already provides, adding little parameter-level meaning beyond it.

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 states a precise verb+resource+mechanism: 'Poll a single property of an instance at a fixed interval for a bounded duration and record every sampled value plus whether it changed.' That is far more specific than the title. However, it never distinguishes itself from close siblings such as watch-value or watch-property-changes, so an agent cannot rule those out from this text alone.

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?

Usage context is concrete and actionable: 'Use this to debug timing/animation/state issues' with three worked examples (Frame.Visible toggling on click, Humanoid.Health dropping, Value object updating). It also warns to keep durations short. It stops short of stating when NOT to use it or naming an alternative tool.

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