agent_loop_preview

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

Annotations already declare readOnlyHint=true, openWorldHint=false, destructiveHint=false, so safety is covered. The description adds two genuine behavioral facts beyond that: the result is deterministic (implying the seed reproduces output) and it uses live instruments rather than samples. It omits whether anything is written to the session, whether audio is rendered, and what the preview returns.

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 front-loaded sentence with no filler, which is good, but it is under-specified rather than concise. The word budget spent on 'native' and 'four-part' would be better spent on parameters or usage.

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?

Two optional parameters with no descriptions, no output schema, and an ambiguous relationship to the other preview/apply tools leave real gaps. An agent knows roughly what domain this touches but not what it produces or when to call it instead of agent_midi_preview or agent_preview.

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 0% — bpm and seed are documented only by min/max bounds. The description's word 'deterministic' hints that seed controls reproducibility, but neither parameter is named, defaulted, or explained, and the bpm-to-loop relationship is unstated. With low coverage the description should compensate and does not.

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 (Preview) and a resource (four-part electronic loop), but the qualifiers 'deterministic', 'native', and 'live instruments' are unexplained jargon. It gives no signal distinguishing it from the many sibling preview tools (agent_preview, agent_midi_preview, agent_repeat_preview, agent_arrange_preview), so an agent cannot tell which preview to pick from the name alone.

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?

No statement of when to use this over alternatives, despite five-plus sibling '*_preview' tools in the same family. There is no mention of prerequisites (loaded instruments? active session?), no note on whether the preview must be followed by agent_apply, and no exclusions.

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