Write transcript + frames to a folder

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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description carries the real burden and does it well: it discloses the exact filenames and frame naming pattern, that a README skeleton is generated, and critically that the video itself is not copied into the folder. It does not say what happens to pre-existing files in outDir (overwrite vs. skip), which is the main remaining behavioral gap for a write tool.

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 sentence, front-loaded with the produced artifacts, with the parenthetical context placed after the actionable content. Nothing is redundant, though the git aside is more workflow flavor than invocation-relevant detail.

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, the description effectively serves as the return contract by enumerating the files written, which is exactly what an agent needs. It is nearly complete for a five-parameter export tool; only overwrite semantics and any return payload remain unstated.

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 100%, so the schema already documents all five parameters including defaults for 'every' and 'width'. The description adds only the mapping of 'every N seconds' to frame cadence and the role of outDir; it does not clarify what 'title' feeds into (presumably the README heading) or the relationship between width and frame output.

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 names a concrete verb (writes) plus the exact artifacts produced: transcript.txt (timestamped), frames/frame_NNN.jpg, and a README.md skeleton, all into outDir. That is far more specific than the title alone and distinguishes it as the composite export step versus single-artifact siblings like brief_frames or brief_transcript, though it never names those siblings explicitly.

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 when-to-use or when-not-to-use statement and no reference to the sibling tools that also produce frames or transcripts. The aside about keeping the folder next to the task and leaving the video out of git hints at a workflow but does not tell an agent when to pick this over brief_frames or brief_transcript.

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