audio_isolation

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

With annotations present (readOnlyHint=false, openWorldHint=true, idempotentHint=false), the description still adds non-obvious context: it consumes ElevenLabs credits and returns audio/mpeg bytes that are saved via output_path or returned inline. That cost/return behavior is not derivable from the annotations. It does not disclose rate limits or failure modes, so it stops 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?

Two short sentences with essentially no filler, and the operative information (output_path saves the returned bytes) is placed clearly. The opening phrase is awkwardly capped and low-value, which keeps it from a 5.

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 six-parameter generation tool with a fully documented schema and no output schema, the description covers cost and return format, which is useful. However, it omits the core operation and any routing versus the parallel stream/stem-separation tools, leaving the agent to infer the tool's actual function.

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 100%, so the schema already documents all six parameters thoroughly. The description only restates the output_path save behavior and the inline-bytes default, adding no syntax or format detail beyond what the schema provides. Baseline 3 is appropriate.

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 lead sentence is essentially the title restated ('Audio Isolation') plus a cost note, so the description never states the actual verb+resource (isolating vocals/speech from a source file) — that meaning lives only in the schema's audio_path description. The only genuinely informative content is about output format, not purpose. Siblings like audio_isolation_stream, separate_song_stems and start_speaker_separation are not distinguished.

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?

There is no guidance on when to use this versus alternatives; the near-identical audio_isolation_stream sibling is never mentioned, nor is there any prerequisite or exclusion. The only quasi-usage note is that you should pass output_path for large files, which is really a parameter hint.

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