Roblox MCP

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

No annotations provided, so description carries full burden. Mentions '[PRO]' tier but does not explain the licensing restriction, failure mode, or what 'watch' returns (stream, callback, events?). No disclosure of cache invalidation behavior or side effects of 'set/add/remove'.

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?

Extremely terse (two fragments) with no wasted words. Front-loaded with basic actions before PRO features. However, brevity borders on under-specification for an 8-parameter polymorphic 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?

Inadequate for tool complexity (8 params, 9 action modes, implied output variants). No output schema is present, yet description doesn't explain return structures for 'details' (hierarchical) or 'context' (properties/source). PRO tier meaning is undefined.

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 has 100% description coverage, establishing a baseline of 3. Description adds minimal value beyond schema—only grouping actions as '[PRO]' vs basic, without explaining parameter relationships or validation rules (e.g., that paths is required for set/add but ignored for get).

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?

Lists specific actions (get, set, clear, context, details, etc.) and implies the resource is 'selection', but fails to articulate what 'selection' refers to (presumably game engine instances given Roblox-style siblings) or how this differs from query_instances or mutate_instances.

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?

Provides no guidance on when to use this tool versus alternatives like query_instances, nor when to prefer 'cached' over 'get', or prerequisites for using 'watch'.

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