Resolve or rediscover a semantic world handle

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

Annotations already establish read-only/idempotent/non-destructive, yet the description adds real behavioral detail beyond them: weak reference resolves immediately, stale handles trigger bounded structural scoring with a hard instance cap, and it explicitly never calls GetDescendants or runs a frame loop. It also routes failure inspection to tool-schema, so the agent knows the cost and limits of the call.

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?

Front-loaded well with purpose first, but the block is dense and contains redundancy: the inline Signature duplicates the input schema, and 'Safety: read-only' plus 'idempotency=read-only' repeat the annotations. The Phase/Requires/Produces meta lines are useful but inflate the size for a single tool.

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 usefully enumerates the return payload (path, expression, class, confidence, staleness, match evidence, runner-up ambiguity, scan counts, truncation) and names prerequisites and failure guidance. It is close to complete, missing only explicit guidance on what confidence values imply for the caller.

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 schema already documents every parameter, giving a baseline of 3. The description mostly restates the same facts (minConfidence reattachment threshold, rediscover=false only reporting staleness, maxInstances cap) and its inline Signature even degrades types to 'any?', adding little conceptual value beyond the schema.

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+resource: resolve a handle returned by observe-world back to its live Roblox Instance. It also distinguishes itself from the producer sibling (observe-world) and from the staleness/rediscovery case, so an agent can pick it without opening 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?

Use condition is explicit: you must hold a handle previously returned by observe-world and an active client, and rediscover=true vs false is spelled out. However it never names alternative tools (e.g. verify-path-exists, search-instances) that might be chosen instead, so it stops short of full when-not guidance.

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