align_inputs

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

Annotations already declare the write/non-destructive/non-idempotent profile, so the bar is lower, and the description usefully adds that the work is queued asynchronously rather than performed inline. It does not say whether the original target file is modified or a new artifact is produced, nor how completion is observed.

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 no wasted words; the action is stated first. It is perhaps slightly too terse for the amount of workflow an agent must reconstruct.

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?

With an output schema present the return payload is covered, and all paths are documented. What is missing is workflow context: how the queued alignment job is tracked to completion, and whether the output is a new file inside the unique run subdirectory.

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 coverage is 100%, so the schema already documents all three paths. The description does add directional meaning — the reference defines the timeline and the target is what gets adjusted — but says nothing about output_dir beyond what the schema states.

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 concrete two-step operation: estimate the sample offset, then write the target aligned to the reference. This distinguishes it from neighbors like matchering_inputs or time_stretch, though the term 'aligned' still requires the reader to infer that the alignment is temporal.

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 choose this over siblings such as matchering_inputs, time_stretch, or create_sample, and no prerequisites or exclusions are mentioned. The agent must infer the use case purely from the operation name.

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