Find functions that reference an Instance (IDA data xrefs)

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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower. The description adds real behavioral context beyond that: the exact referrer-detection rule (upvalue OR constant), the per-xref return shape (__fnInfo fields plus 'via'), and the scan cap with truncation flagging. It stops short of stating expected runtime cost magnitude or what a truncated result looks like structurally.

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 behavioral core is front-loaded and every early sentence earns its place; the signature restatement and boilerplate metadata (Phase/cost/Produces, 'On failure: inspect tool-schema') are somewhat redundant. Still appropriately sized for a medium-cost scan 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?

No output schema exists, and the description compensates by naming the __fnInfo fields and the 'via' discriminator, so an agent knows what comes back. Requirements and constraints are covered; only edge behavior (truncation signal shape, error cases beyond type mismatch) is left implicit.

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 all four parameters are documented in the schema, so the baseline is 3. The description adds the important semantic that instancePath is a Luau expression yielding an Instance, but re-lists the signature redundantly rather than clarifying unknown limits beyond the schema (e.g. what threadContext changes).

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 chain (resolve an Instance, walk every GC function, report referrers) and identifies the resource precisely. The IDA data-xref analogy and the 'upvalues OR constants' criterion distinguish it from sibling xref tools like find-upvalue-xref, find-constants-xref, and find-function-xrefs 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?

Gives a clear usage frame ('which functions read, manipulate, or watch this object?') and prerequisites (active-client, resolved-target, requires getgc + getupvalues/getconstants), which tells the agent when it applies. It does not, however, explicitly route the agent away from the narrower per-mechanism siblings (find-upvalue-xref, find-constants-xref) when a single mechanism is what's wanted.

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