create_sample

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

Annotations already declare the safety profile (not read-only, not destructive, closed-world, not idempotent). The description adds genuine context beyond that: this is a queued/asynchronous operation, and it writes into a unique output subdirectory so prior runs are not overwritten — which aligns with idempotentHint=false. It stops short of saying how the queued work is tracked, which is the detail an agent most needs.

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 zero padding — the action leads and the output-directory caveat follows. It is efficient, though its brevity comes partly from omission rather than discipline.

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?

An output schema exists and annotations cover safety, so return shape is not the description's job. Still, for a job-queuing tool the description should say results are retrieved asynchronously via the job siblings; without that, an agent knows what it does but not how to finish the workflow.

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 audio_path, output_dir, offset_seconds, and duration_seconds are all documented in the schema itself. The description's only parameter-adjacent content is the "unique output directory" note, which repeats the output_dir schema text rather than extending it. Baseline 3 applies.

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?

"Queue a real preview clip" gives a verb (queue) and a resource (preview clip), so the basic action is inferable. But it never differentiates itself from nearby siblings such as analyze_audio, probe_audio, or start_separation, and the qualifier "real" adds no discriminating information.

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 statement of when to use this versus the many other audio-processing siblings, and no prerequisites. The word "Queue" hints at an async job, but nothing tells the agent to poll get_job or list_jobs afterwards, which is essential to using it correctly.

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