inspect_fileDetect the format of a subtitle/transcript/EDL/FCPXML file and report what CutConvert would produce from it, without performing the conversion or using quota.
| Name | Required | Description | Default |
|---|---|---|---|
| content | No | File content (text formats). | |
| filename | Yes | Original file name including extension. | |
| content_base64 | No | Base64 bytes (binary formats like .prtranscript). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already covers non-mutation, and the description adds that the tool does not use quota, which is valuable cost-related context. It also clarifies it only reports, not executes, the conversion. This goes beyond the annotation and provides useful behavioral detail.
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 single, well-structured sentence that front-loads the core purpose and immediately states key constraints (no conversion, no quota). It contains no unnecessary words 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?
With no output schema, the description informs the agent that the tool returns a report of what CutConvert would produce, which is essential for understanding the result. It also notes quota behavior. It doesn't specify edge cases (e.g., unknown formats), but for a detection tool this is adequate.
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 input schema fully describes all three parameters (content, filename, content_base64) with clear meanings, giving 100% schema coverage. The description adds no extra information about parameters, so it stays at the baseline of 3 as the schema handles the semantics.
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 a specific action (detect format) and a specific resource (subtitle/transcript/EDL/FCPXML files), and explicitly distinguishes it from conversion by noting it does not perform conversion. This separates it cleanly from the sibling tools convert_file, list_converters, and timecode_calculate.
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 indicates when to use this tool ('without performing the conversion') and mentions it reports what CutConvert would produce, implying it's a pre-conversion inspection. It does not explicitly name alternatives, but the purpose is clear enough for an agent to infer that convert_file is for actual conversion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a clearly distinct operation: converting, inspecting without conversion, listing conversion options, and performing timecode math. There is no meaningful overlap even between convert_file and inspect_file because inspect explicitly avoids conversion.
Three tools follow a clean verb_noun pattern: convert_file, inspect_file, list_converters. timecode_calculate breaks that pattern by placing the noun first, though it remains readable and unambiguous.
Four tools is well-scoped for a specialized conversion utility. Each tool earns its place and the set is neither bloated nor too thin.
The tool surface covers discovery (list_converters), preflight/inspection (inspect_file), execution (convert_file), and a common adjacent utility (timecode_calculate). No obvious dead ends or missing lifecycle operations for the stated domain.