Builds a JSON edit-planning context with utterances and word indexes, enabling transcript-driven cut tools to locate and edit podcast audio precisely.
Build the JSON edit-planning context: utterances with word indexes for cut_* tools.
| Name | Required | Description | Default |
|---|---|---|---|
| project_path | No | ||
| max_utterances | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.1Input schema / properties / project_path / anyOfAdded value: +[
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / project_path / defaultAdded value: +nullInput schema / properties / project_path / typeRemoved value: -"string"Input schema / requiredRemoved value: -[
- "project_path"
-]v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses the content it assembles but says nothing about whether this is a read-only/idempotent computation, whether it mutates session or project state, or whether it requires specific permissions – meaningful gaps for a 'build' verb that could imply a write.
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 dense sentence that front-loads the action and immediately qualifies the output and its consumers. No filler or redundancy.
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 description correctly identifies purpose and downstream consumers. But with no annotations and 0% parameter coverage, an agent still lacks guidance on the two inputs and on the tool's side-effect profile.
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 neither of the two parameters (project_path, max_utterances) is mentioned in the description. The passing reference to 'utterances' loosely relates to max_utterances but conveys no default or format, so the description does not compensate for the documentation gap.
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 gives a specific verb+resource ('Build the JSON edit-planning context') and even states the payload contents ('utterances with word indexes'), which distinguishes it from the many cut_*/apply_* siblings. It stops short of explicitly naming which sibling it feeds versus the other context-producing tools, so it is clear but not fully differentiated.
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?
By naming the 'cut_* tools' as consumers, it implies this is a prerequisite step to run before those tools. However, it never states when to call it versus alternatives (e.g., other propose_/preview_ tools) or any precondition/exclusion, leaving usage to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.