Run a Luau script on N clients in parallel

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

Goes well beyond the annotations: discloses the 8-in-flight concurrency cap, per-client scriptToken/RPC budget isolation, pre-flight validation that catches typo'd mcp.* calls before fanout, and the MUTATING/no-idempotency nature of writing live client state. Annotations already flag destructive/non-readOnly, and the description adds the operational constraints an agent needs.

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 core purpose and target selection before the return shape and metadata tail. The trailing 'Phase/cost/Requires/Produces/Verify' line and the signature block partly duplicate the schema and annotations, costing a little tightness, but every section is scannable and purposeful.

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, yet the description fully specifies the return shape ({results: [...], summary: {...}}), the failure mode, and the prerequisites. For a high-cost mutating fanout tool with 6 params, nothing an agent needs to invoke it correctly is missing.

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 source, clients, rpcBudget, timeoutMs, persistent, and threadContext with defaults and bounds. The description's signature block largely restates the schema rather than adding new semantics, so the baseline 3 applies.

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 (Run), resource (ONE Luau program), and scope (across multiple connected clients in parallel) with the return shape named. It is clearly separable from single-target siblings like execute, run-luau, and batch-execute.

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?

Explicitly explains how targets are selected (explicit clientId array from list-clients vs the 'all' sentinel) and gives the failure path (inspect tool-schema, verify with assert-state). It does not, however, contrast itself against near-neighbors such as batch-execute or run-on-actor, so the when-not guidance is only implied.

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