localize_subtitles

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

No annotations are provided, so the description carries the burden. It discloses the in-memory nature, the optional output_dir behavior (write one .srt per language), and the STT fallback when no subtitle file is given. However, it does not disclose side effects, whether output_dir writes are destructive, or what the return value contains despite an output schema existing.

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 compact and front-loaded with the core purpose, followed by a concise parameter list. The parameter list is useful and not redundant with the schema because it adds semantic context. It could be slightly tighter, but every sentence earns its place.

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?

Given 8 parameters, no annotations, and an output schema, the description covers the main input modes and output_dir behavior. It lacks guidance on required vs optional combinations (e.g., is video_path required if no subtitle_path?), what happens when both are provided, and what the return value contains. The output schema exists but the description doesn't clarify the in-memory result structure.

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%, so the description must compensate. It explains the role of subtitle_path, video_path, glossary_path, context, formality, output_dir, and target_language_codes, adding meaning beyond the bare schema titles. It does not explain source_language_code's default behavior or the exact format of target_language_codes beyond the example, but the coverage is strong.

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 states a specific verb ('Localize') and resource ('subtitles'), and clarifies the in-memory nature of the operation. It distinguishes itself from siblings like translate/translate_batch by focusing on subtitle localization with optional STT from video, though it doesn't explicitly name a sibling alternative.

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 implies usage: provide an SRT/ITT and/or a video, with video used when no subtitle file is given. It does not explicitly state when to prefer this over translate/translate_batch or other siblings, nor does it mention exclusions or prerequisites like needing a registered video or supported language codes.

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