manage_audio

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

There are no annotations, so the description carries the full burden. It adds behavioral context by specifying valid sound ID formats and the listener type options for set_listener. However, it does not disclose side effects of actions (e.g., whether stop_all affects all sounds globally, whether create is reversible, or what errors occur for invalid IDs). The action names imply some behavior, but deeper consequences remain undocumented.

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?

A single sentence front-loads the purpose ('Manage Sound instances') and then efficiently enumerates actions and key constraints. There is no wasted wording; every clause adds useful information. The semicolon-separated structure keeps it compact while covering a broad action set.

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 listing actions and some constraints, the description omits critical context for a tool with 9 parameters and no output schema. The 'set' action is undefined (what properties can be set?), the return values for 'list', the behavior of 'path' vs 'parentPath', and the format of the free-form 'properties' object are unexplained. The description is too skeletal for an agent to use every action correctly without further inference or trial-and-error.

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 coverage is only 33%, and the description does add meaning for some parameters: it clarifies that soundId can be a number or 'rbxassetid://...' and describes listenerType values. Yet many parameters like name, path, parentPath, properties, and cframe are not explained in the description beyond the schema, leaving significant gaps. The description partially compensates but not enough for a 9-parameter tool with low schema coverage.

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 clearly states the resource ('Sound instances') and provides a comprehensive verb-based list of actions (create, play, pause, resume, stop, stop_all, list, set, set_listener). This distinguishes it from sibling tools that operate on other resource types such as terrain, lighting, or physics.

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 gives specific usage constraints: 'do not invent IDs' and 'Prefer user-provided or search-accepted asset IDs' for the create action. It also lists all possible actions, making it clear when to use this tool. However, it does not explicitly mention when not to use it or describe alternatives like mutate_instances, so it falls short of an explicit exclusion statement.

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