label_split_regions

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

With no annotations provided, the description carries the full burden. It clearly discloses the non-destructive nature ('without removing anything'), clarifies that it acts on the current selection and selected tracks, and notes labels stay in place. This is strong behavioral disclosure. It doesn't mention whether existing clips without labels are affected or how splitting interacts with adjacent unlabeled audio, but the core mutation behavior is transparent.

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 compact — roughly 50 words in a title line plus three supporting sentences. Information is front-loaded with the core action in the first line, followed by crucial state prerequisites and the non-destructive clarification. Every sentence earns its place. It's slightly redundant with 'the labels themselves stay where they are' restating the non-destructive point, but that reinforcement is justified given the destructive sibling context.

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 no parameters and no output schema, the description appropriately focuses on state requirements (selection, tracks) and behavioral effects. It adequately covers the main concerns: what it does, what it doesn't do (delete/move), and prerequisites. It doesn't describe the resulting clip structure in detail, but for a 0-parameter tool with this action, the description is well-rounded and sufficient.

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 0 parameters and 100% schema coverage (vacuously), so the baseline for zero-parameter tools is 4. The description appropriately channels all state into the current selection and selected tracks rather than parameters, and explains this clearly. No parameter documentation is needed since there are none.

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 clearly states the verb ('Split'), the resource ('audio clips'), and the trigger ('at every label boundary'). It distinguishes from siblings like label_cut_regions, label_delete_regions, and label_silence_regions by explicitly noting it 'prepares segment boundaries for separate handling without removing anything' and that 'labels stay where they are' — differentiating it from destructive or label-moving operations such as label_join_regions.

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?

The description gives clear operational context: acts on labeled regions within the current selection on SELECTED AUDIO TRACKS, with explicit prerequisite instruction to 'select the audio tracks and time range first'. It doesn't name alternatives explicitly, but the non-destructive phrasing implicitly contrasts with destructive region tools among siblings. It lacks an explicit when-not-to-use statement, which keeps it from a 5.

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