extract_frames

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

With no annotations, the description carries the full burden, and it does disclose useful behavior: default output directory ('name.frames' beside the input), the exact output filename patterns, and that max_frames exists to prevent thousands of files. However it never mentions `overwrite` (default false — what happens to existing files?), `dry_run`, or `timeout_s`, all of which materially affect a tool that writes files to disk.

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 mode-selection logic is front-loaded in the first two sentences and the remaining details are packed into short parenthetical clauses with no filler. The heavy use of inline parentheses makes it denser to scan than a bulleted layout would be, but nothing is redundant.

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 no explanation, and the frame-selection and naming behavior is well covered. For a 10-parameter tool with zero annotations that writes files to a directory, leaving overwrite semantics, dry_run and timeout unaddressed is a real gap an agent would have to guess about.

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% across 10 parameters, so the description must compensate and largely does: it explains `times` accepts numbers or timestamp strings like "0:01:30", `every_s` starts at 0, `format` defaults to png, `width` preserves aspect ratio, and where `output_dir` points by default. Three parameters — dry_run, overwrite, timeout_s — get no explanation at all, so the coverage is good but incomplete.

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 opening line gives a precise verb and resource: 'Save still images (thumbnails) from a video.' That unambiguously separates it from siblings like extract_audio, make_gif and trim without needing to name them. It stops short of explicitly routing against a sibling, so it is clear but not sibling-differentiated by name.

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?

It clearly explains the three mutually exclusive modes — explicit `times`, uniform `every_s` sampling, or the fallback single middle frame — which is exactly the decision an agent must make before calling. It gives no guidance on when to prefer this tool over transform/make_gif, so it is strong on intra-tool context but silent on alternatives.

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