Inspect a local MP4 or MOV

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

Annotations already declare read-only, idempotent, non-destructive and closed-world, so the bar is lower, yet the description still adds real behavioral detail: bounded sampling, no packet contents or metadata text returned, and rejection of nonidentity edit lists to avoid exposing hidden media. That is exactly the kind of refusal semantics an agent cannot infer from annotations.

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 tight sentences, with the core scope front-loaded and each subsequent sentence contributing a distinct fact (return shape, refusal behavior, environment requirement). No filler.

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 appropriately characterizes return values ('counts and technical headers'), discloses the privacy-motivated refusal path, and confirms no browser is needed. For a single-parameter read tool, an agent has everything required to call it correctly.

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 one parameter and schema coverage is 100%, with the schema itself explaining that absolute local paths are required and URLs/network shares are refused. The description adds no further meaning about input_path, so the baseline 3 applies.

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 (Inspect) and a precisely scoped resource (bounded MP4/MOV sample tables, track geometry, codecs, timing) with the explicit exclusion of decoding video/audio. This clearly separates it from abox_gif_inspect, abox_exif_inspect and abox_dicom_inspect, which target different containers.

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 clear conditions of use ('without decoding', 'requires no browser') and the refusal boundary for nonidentity edit lists. It does not explicitly compare itself to sibling tools like abox_video_remux or abox_video_trim, so the when-to-use-vs-alternative routing is implied rather than stated.

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