label_split_regions

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

With no annotations, the description carries the full burden. It discloses that the operation is non-destructive ('without removing anything'), that labels remain unchanged ('The labels themselves stay where they are'), and that it acts on selected tracks and time range. This goes beyond the obvious implication of the name, providing useful behavioral detail for a zero-parameter tool.

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?

The description is a compact paragraph with no fluff. The main action is front-loaded in the first sentence, followed by essential clarifications (non-destructive, scope, preconditions, label behavior). Every sentence adds value and there is no redundant restatement of the tool name.

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?

Given the tool's simplicity (zero params, no output schema) and the presence of many sibling tools, the description covers the key points an agent needs: what it does, that it's non-destructive, that it requires a selection and selected tracks, and that labels persist. It could mention that splitting results in separate clip regions, but that is implied and not critical. Overall, it is sufficiently complete for reliable invocation.

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?

The tool has zero parameters, so the input schema is trivially complete (100% coverage). The description does not need to add parameter-level meaning, and it correctly omits any param details. Baseline for no parameters is 4.

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 opens with a precise verb+resource: 'Split the audio clips at every label boundary.' It clearly differentiates from sibling edit tools (like edit_split) by specifying the label-driven trigger and the non-destructive nature ('without removing anything'), and from label manipulation tools (e.g., label_cut_regions, label_delete_regions) by the phrase 'without removing anything' and 'labels stay where they are.' The scope is also explicit: acts on labeled regions within the current selection on selected tracks.

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 gives explicit preconditions: 'select the audio tracks and time range first.' It also implies when to use it by stating it does not remove anything, which suggests using this tool when you need to split without deletion. However, it does not explicitly name alternative tools for cases where deletion is desired (e.g., label_cut_regions, label_delete_regions), so it lacks full when-not guidance.

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