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

With no annotations supplied, the description carries the full burden and does well: it discloses per-started-minute billing at €0.02 charged to the Bearer API key, that burn produces an MP4, and that translation is English-only. It omits turnaround/asynchrony, input size limits, and whether the burned MP4 is returned as a URL or 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?

Purpose and billing lead, followed by a compact parameter glossary, so nothing is buried. The long em-dash run-on and inconsistent units (font_size and max_chars described numerically while the schema types them as strings) cost a point.

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?

For an 8-parameter media tool with an output schema, this covers purpose, cost, defaults, and mode behavior well enough to invoke correctly. The one gap is that url is implicitly mandatory while the schema marks no required fields, and nothing clarifies that mismatch.

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 coverage is 0%, yet the description documents all eight parameters with defaults and allowed ranges: mode srt/vtt/burn, language ISO with auto default, translate to English, max_chars 16–80 default 42, font_size 12–72, position bottom/middle/top, and hex color default FFFFFF. It also flags which parameters only apply in burn mode, which the bare schema cannot convey.

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?

"Transcribe a video or audio, wrap cues to 42 chars, return SRT/VTT or burn styled subtitles into an MP4" states a concrete verb, resource, and output set, so the agent knows exactly what comes back. It never names a sibling (caption, speech_to_text, video_clip) to differentiate, which keeps it just below the top score.

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?

Targeting is implied by "for Reels and Shorts" and the mode list, which hints at vertical-video captioning versus plain transcript delivery. There is no explicit when-not guidance and no routing to alternatives such as speech_to_text for audio-only transcription or translate for text translation.

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