Make a local time-lapse video

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

Annotations only declare the generic non-readOnly/non-destructive/non-idempotent profile; the description adds substantive behavior: audio and metadata are dropped, output frames and timing are verified, runs are refused below two frames, and the environment needs a local browser with native H.264. That is exactly the context annotations cannot convey.

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?

Front-loaded with verb and resource, and most sentences carry real constraints (silent output, frame-count refusal, local-browser requirement). The 'reuses the website frame-selection and encoding engines' clause is internal implementation detail that doesn't help tool selection.

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 a mutating, non-idempotent tool with no output schema, it covers environment, input restrictions, what is stripped from the source, and validation. The notable gap is what happens to an existing file at output_path (overwrite vs. refuse), which an agent needs before calling.

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?

Only 33% of params are schema-documented (the two paths), so the description carries the burden for speed, frame rate, max side, and quality — and it does name all four as the explicit controls alongside 'silent' output. It still doesn't explain semantics such as speed being a multiplier or units, so it doesn't fully close the gap.

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?

States a specific verb and transformation ('Speed up admitted H.264 video into a silent new H.264 MP4') plus the tunable dimensions, which clearly separates it from siblings like abox_video_compress, abox_video_trim, or abox_video_reverse. It never names a sibling explicitly, so it stops just short of a 5.

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?

Gives real preconditions: input must be 'admitted H.264', requires a local browser and native H.264 encoding, and it refuses fewer than two planned frames. It does not route the agent to an alternative (e.g., an image-sequence or GIF path) when those preconditions fail, so no explicit when-not guidance.

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