Clean AI generator artifacts

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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=true; the description adds genuinely new behavior: the no-credit cost model, the guarantee that loudness/tone are untouched, and the asynchronous job-id/polling contract. It does not discuss failure modes or what sensitivity changes, keeping it short of a 5.

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?

Front-loaded with the core action and no filler sentences; each clause (what is removed, what is preserved, cost, follow-up) carries information. The parenthetical artifact list makes the middle dense, but nothing is wasted.

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 3-param async job tool with annotations and an output schema, the description covers scope, cost, preservation guarantees, ethical caveat and the polling handoff. Remaining gaps are the undocumented out_format/sensitivity parameters, which the output schema cannot cover.

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 67%: audio_url is well documented and enriched with share-link resolution behavior, but out_format (enum) and sensitivity ('0-1, default server-side') are undocumented. The description adds no parameter-level detail to compensate, so it sits at the baseline.

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 ('remove the marks an AI generator leaves in the audio') and enumerates exactly what those marks are (narrow tones above 15 kHz, level jumps at block seams, fixed spectral peaks). An agent can distinguish this from analyze_track or master_track without opening any schema.

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?

Gives clear operating context: it preserves loudness and tone, it does not conceal AI provenance, it never spends a credit, and the result must be polled via get_job. It stops short of explicitly naming when to choose this over a sibling like master_track, so it is context-rich but not fully routed.

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