mutate_instances

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

No annotations are provided, so the description alone must disclose behavior. It reveals the types of operations (including irreversible ones like delete) and accepted property value formats, but it does not warn about permanence, workspace impact, or permission requirements. This is a moderate level of transparency.

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 description is a single run-on sentence combining a list of actions and a property-value guide. While all information is relevant, it lacks bullet points or sectioning, making it harder to parse. The core actions are front-loaded, but the mid-sentence 'Also:' list is dense.

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?

Given the tool's high complexity (23 params, 13 sub-actions), the description is under-specified. It lists sub-action names but does not explain which parameters each sub-action requires (e.g., scatter needs templatePaths, region, count) or provide usage examples. The schema's param descriptions partially compensate, but the action-param mapping 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?

The description adds important value-format semantics for the 'properties' parameter (Vector3, CFrame, Color3, UDim2, enums) which are absent from the schema's generic property object. It also redundantly lists the action enum values, which are already in the schema, but the property-format information significantly enhances parameter handling.

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 opens with a clear enumeration of mutation verbs ('Create, delete, clone, move, rename, or pivot instances'), explicitly establishing the tool's scope as structural mutation of instances. It further distinguishes from siblings like query_instances by focusing on mutation operations.

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?

The description implies when to use the tool (when you need to mutate instances) but does not explicitly state alternatives or exclusions. The list of sub-operations (create_with_props, mass_create, scatter) gives context for specific actions, but no guidance on when to choose this over manage_properties or other tools.

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