Replace an object's raw metatable (MUTATES live state)

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

Goes well beyond annotations (destructiveHint=true, readOnlyHint=false, idempotentHint=false) by naming the concrete mechanics: bypasses __metatable lock, swaps __index/__namecall/__newindex wholesale, can break the client, severs security routing, is an anticheat signal, and requires confirm=true or it refuses. Also discloses the return shape { Target, ok } / { error }. Minimal tension: the trailing 'idempotency=idempotent-write' sits awkwardly against idempotentHint=false, but this is a labeling nuance, not a safety contradiction.

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-loads the danger and the core action, and most sentences carry distinct information (mechanics, risk, RE workflow, confirm gate, return values). The trailing metadata block (Phase/cost/idempotency/Requires/Capabilities/Produces/Verify/On failure) is dense but partly redundant with structured fields, keeping it from a 5.

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?

Despite no output schema, the description states the return shape, the mandatory confirm gate, prerequisites (setrawmetatable, writable target, resolved target), and failure behavior. For a destructive live-state mutation tool, an agent has everything needed to invoke it correctly and safely.

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 all four parameters with examples and the confirm safety gate. The description's inline signature and confirm restatement add little beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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+resource: resolve a Luau expression to an object and REPLACE its entire metatable via setrawmetatable, bypassing any __metatable lock. This is clearly distinguishable from siblings like get-metatable, inspect-instance-metatable, hook-metamethod, and set-metatable-readonly. An agent knows exactly what this does versus neighbors.

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 concrete when-to-use pattern ('clone the existing metatable, modify a metamethod, then set it back') and a prerequisite chain (target metatable may need to be writable — see set-metatable-readonly; requires setrawmetatable). It stops short of naming an explicit alternative to prefer for lighter-touch cases (e.g. hook-metamethod), so it is strong context without full when-not routing.

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