split_chapters

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

With no annotations, the description carries the full burden. It does disclose the side effect of writing files to a specific path and what those files contain, which is valuable, but it never states prerequisites (must a run/transcript already exist?), overwrite behavior on re-run, or what happens if no chapter marker is found.

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?

Two sentences, zero filler: the first front-loads what is produced and where, the second gives the usage rationale. Every clause adds information an agent would otherwise have to infer.

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, so return values need not be explained, and the file-artifact description is good. But for a tool whose sole input is an opaque 'run' string with no annotations, the missing prerequisite and re-run semantics leave meaningful gaps in calling it correctly.

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% and the single required parameter 'run' is never mentioned in the description. The agent must guess that it is a run identifier from a prior transcribe/run_status step; the description provides no clarification of format or origin.

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 names a specific verb and resource ('Tách transcript dài thành từng chương'), the exact marker it splits on ('mốc «Chương <số>»'), and the resulting artifacts (transcript/chapters/chuong-XXXX.txt plus character counts, timestamps, audio-minute estimates). No sibling tool in the list produces chapter files, so an agent can identify this immediately.

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 states a clear trigger condition: use it when the story is long and has many chapters, so that each chapter can be read/rewritten individually instead of the whole file. It does not say when NOT to use it (e.g., short single-chapter transcripts) or name a fallback alternative, which keeps it below a 5.

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