manage_audio

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

Annotations already communicate that the tool is not read-only and not idempotent. The description adds some behavioral context by mentioning 'play/stop', 'add', 'configure', and 'author', which imply state-changing and asset-creating operations. However, it does not disclose side effects such as saving assets, required permissions, or reversibility, so it only marginally exceeds annotation-provided information.

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 sentence that names the major functional areas without unnecessary verbosity. It is front-loaded with the most common actions ('Play/stop sounds') and remains compact given the tool's breadth. The run-on list is somewhat dense but not unwieldy, and every phrase contributes a distinct category.

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?

For a tool with 60 parameters, 48 action variants, and no output schema, this description is far from complete. It provides only a high-level overview and does not explain action-specific behavior, return values, or side effects. Even with the annotations, an agent would struggle to know which parameters are required for a given action or what the result will be.

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?

With 60 parameters and schema description coverage at 48%, the description was expected to compensate for undocumented fields, but it does not. It offers no explanation of parameter usage, relationships, or action-specific required inputs. The description's high-level categories (e.g., 'spatial audio') loosely map to some parameters but provide no concrete semantic help for invoking the tool correctly.

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 identifies the tool's domain and primary actions: playing/stopping sounds, adding audio components, configuring mixes/attenuation/spatial audio, and authoring Sound Cues/MetaSounds. It distinguishes itself from sibling tools by naming audio-specific resources and operations, though it remains a broad umbrella for many sub-actions.

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 no explicit guidance on when to use this tool versus alternatives. It implies audio-related tasks but does not state exclusions, prerequisites, or complementary tools. The lack of any 'when-to-use' or 'use instead' language leaves the agent to infer from the tool name alone.

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