Crop a local H.264 video

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

With annotations present, the description goes well beyond them: it discloses verification behavior (coded geometry check pre-decode, frame/time and audio-packet verification) and two real side effects an agent must know — 'Color can change and unselected metadata is omitted.' It does not state whether an existing output_path is overwritten, which is the main remaining behavioral gap.

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?

Four sentences, front-loaded with the operation and output before verification details and caveats. Dense but each sentence carries information; minor jargon ('admitted', 'coded geometry') adds parsing cost without adding precision.

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 mutation tool with no output schema and five parameters, the description covers inputs, side effects, verification and environment prerequisites. Missing only return-value shape and overwrite behavior, both of which matter for a write tool but are secondary to what is already disclosed.

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 coverage is 60%, so baseline is roughly 3. The description adds real meaning for crop_path ('exact local JSON coordinates in the decoded display image') and hints at keep_audio via 'any copied audio packets', but says nothing about the quality enum or the overwrite semantics of output_path.

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 resource ('Crop an admitted H.264 MP4/MOV ... write a re-encoded MP4') plus the crop coordinate source, which clearly separates it from siblings like abox_video_rotate_bake or abox_video_trim. It never names a sibling explicitly, so differentiation is inferred from the operation itself rather than stated.

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?

Usage is implied by the operation and constrained by a format restriction (H.264 MP4/MOV only) and a prerequisite ('Requires a local browser with native H.264 support'), which is genuinely useful gating. However, there is no explicit statement of when to prefer this over a rotate-bake or trim workflow, nor any exclusion beyond format.

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