ffmpeg_convert

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

Annotations already declare this is a mutating operation (readOnlyHint=false) in a closed world, and the description correctly adds the external dependency ("Requires ffmpeg") which annotations cannot express. However, it says nothing about the write side effects that matter for a transcoder: whether the output path is overwritten if it exists, whether directories are created, or whether a failed ffmpeg call leaves a partial 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?

A single front-loaded sentence plus a short prerequisite note; the fallback role comes first, examples second, and there is no redundant restatement of the tool name. Every clause carries information.

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 and thin parameter documentation, the description should do more: it never says what the tool returns (output path, ffmpeg log, or nothing) or how failures are surfaced. For a low-level escape hatch that can silently produce broken or partial media, that is a real gap, though the examples and prerequisite note cover the essentials of selecting and calling it.

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 only 33%, with the two required parameters (input, output) carrying no schema documentation at all; the description partially compensates by implying these are file paths for a transcode and by illustrating the kinds of flags that belong in args. It still never states whether input/output are absolute paths, project-relative paths, or whether the extension drives the output format.

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?

"Transcode a file with ffmpeg" gives a specific verb and resource, and the parenthetical examples (AV1/VP9/WebM, DivX/DV input, mp3 extraction) make the scope concrete. The framing as a fallback for FilmCraft's native tools is a meaningful qualifier, but it does not distinguish this from the sibling ffmpeg_run, which appears to overlap heavily.

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?

"Fallback for what FilmCraft can't do" is explicit when-to-use guidance: reach for this only after the native tools are insufficient, and the format examples clarify the kinds of jobs that qualify. It stops short of naming ffmpeg_run as the alternative or stating any exclusions, so the agent still has to guess which of the two raw-ffmpeg tools to pick.

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