auto_cleanup_podcast

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

With no annotations, the description carries the full burden, and it delivers: it discloses that the tool runs in the background, returns a job_id immediately, and details the processing chain with concrete parameters (-16 LUFS Apple Podcasts target, 4:1 compression, clip-safe fallback). It even surfaces a critical precondition about the first 0.5s needing to be room tone/silence. The only gap is that it never says what audio the pipeline operates on (selection vs. whole track) or whether the result is destructive or written to a new file.

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?

Every sentence earns its place: purpose and async behavior are front-loaded, the pipeline is compressed into a single arrow-separated line, and the parameter details are cleanly separated. The IMPORTANT warning justifies its emphasis. No filler or repetition of schema data.

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 one-parameter background job, the description covers the invocation essentials: the pipeline, the monitoring path, and the parameter precondition. But with no annotations and no output schema, material gaps remain — nothing states the input scope (selection, track, or project), whether the operation is destructive, or where the processed audio output lands, all of which an agent needs to invoke correctly and set expectations.

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%, so the description must fully compensate, and it does. For remove_noise it explains the mechanism (uses first 0.5s as noise profile), states the default (True), and flags a critical usage precondition (first 0.5s must be room tone/silence). This adds real semantic depth far beyond the bare boolean in the schema.

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 states a specific action ('ONE-CLICK PODCAST CLEANUP') on a specific resource (podcast audio) and enumerates the exact pipeline stages (DC offset, noise reduction, compress 4:1, LUFS loudness). The 'podcast' target distinguishes it from siblings like auto_cleanup_interview and auto_cleanup_vocal, though it never explicitly says 'use this for spoken-word podcast content.'

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?

It clearly instructs the agent to use check_pipeline_status after invocation to monitor the background job, which is genuinely useful routing guidance. However, it gives no conditions for when to pick auto_cleanup_podcast over the many sibling auto_cleanup_* variants (audio, interview, vocal, live), so the when-vs-alternatives guidance is only implied by the name.

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