export_loop

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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds genuinely new behavioral facts: the exact encoding, that the transfer is slow (30 s loop takes a while), and that pedal control data is appended after the audio for lossless re-import. The only mild tension is that "Save ... to a WAV file" implies a file write while readOnlyHint is true; it is plausibly a read of pedal state producing an artifact rather than a device mutation, but the description never resolves that.

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?

Two sentences, both dense with information: format and medium first, then the round-trip guarantee. No filler, no restatement of the tool name, and the slow-transfer warning is placed where it will be read before invocation.

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 low-complexity export tool with no output schema and strong annotations, the description covers format, medium, timing, and data layout well. It leaves the entire "file" parameter unexplained and does not indicate what a successful call returns or where the file ultimately lands, which are real gaps for an agent trying to invoke it correctly.

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% for the two parameters, so the description must carry the load and does not. The optional "file" string is never explained (path? filename? USB-relative? default?), and "loop" (integer 1–10) is only obliquely implied by the word "loop" — the description never says it is a loop slot number in that range.

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 and resource ("Save a loop") plus the concrete output format ("24-bit stereo 44.1 kHz WAV file"), which distinguishes it from siblings like export_sample, import_loop, and list_loops without any schema lookup.

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?

Names the complementary sibling explicitly — the appended control data exists "so import_loop can restore it exactly" — which tells the agent this is the outbound half of a round-trip. Also implies the practical context (USB medium, slow for a 30 s loop). It does not, however, contrast itself with export_sample or say what to do when no USB path is supplied.

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