convert_subtitle

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

With no annotations provided, the description must disclose behavioral traits. It mentions it supports encoding and time offset, but does not state whether it modifies the input file, creates a new output file, or produces any side effects. There is no mention of error handling, permissions, or reversibility. This is a significant gap for a conversion tool that likely writes a new file.

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 one concise sentence that front-loads the purpose and key capabilities. It contains no fluff or redundancy. It effectively summarizes the tool's domain and features without unnecessary detail, earning maximum conciseness.

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?

The tool has a nested options object with four sub-parameters, but the description does not explain their relationship or typical usage. There is no output schema or description of return values (e.g., whether it returns a path, success indicator, or error). The tool's behavior around output_path being optional is not mentioned. This is incomplete for an agent to correctly invoke it without relying heavily on the schema.

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 schema has descriptions for input_path, output_path, and output_format, and options has named sub-parameters (fps, encoding, language, time_offset) with their own descriptions, so coverage is high. The description adds little beyond the schema, only reaffirming encoding and time offset features. It does not clarify the meaning of time_offset (e.g., seconds, can be negative) or the format of fps, which the schema already handles. At 75% coverage, baseline 3 is appropriate.

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 it converts subtitle formats (SRT/ASS/SSA/VTT) and mentions encoding and time offset. It is specific enough to distinguish from sibling media/document converters. However, it does not explicitly state whether these are input or output formats, and it omits the primary output formats (srt/ass/vtt) that appear in the schema.

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?

There is no explicit guidance on when to use this tool versus alternatives. It simply says 'subtitle format conversion' and does not mention conditions like 'use when you need to convert subtitle files' or list alternatives to avoid. The tool name and sibling list provide context, but the description itself offers no exclusions or recommendations.

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