Cut reels from a long video

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

Annotations only cover safety (not read-only, open-world, non-destructive); the description adds the real behavioral facts: local file processing, vertical 1080x1920 output, a hook/on-screen text/caption per reel, ffmpeg dependency, and file paths returned. It does not mention runtime, cost, or what happens if ffmpeg is absent, but the core traits are disclosed.

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?

Three front-loaded sentences covering the primary mode, the manual override, the layout semantics and the handoff dependency. Dense but efficient; the layout clause sits slightly awkwardly mid-paragraph rather than in a separate structure.

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?

Enough to select and invoke the tool for the main path, and the return value is described despite no output schema. However, with 9 parameters and near-zero schema descriptions, an agent must open the schema to learn the defaults and bounds for count, min_seconds, max_seconds and template.

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 only 11%, so the description carries the burden, but it explains just a subset: clips start/end, transcript_path, file_path and layout (crop, blur). It omits count, min_seconds, max_seconds, template, and the third layout value 'original', leaving half the parameters undocumented anywhere.

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: finds standalone moments in a long local video and cuts vertical 1080x1920 reels with hook, on-screen text and caption. It also names the handoff target (publish_reel) and the exact-cut alternative mode, so it is clearly distinguishable from the publish_* siblings.

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 two clear usage modes: automatic moment discovery, or passing clips with start/end seconds to cut exactly those. It also flags the ffmpeg prerequisite and that the source can be a transcript file. There is no explicit when-not-to-use or named alternative among siblings, which keeps it at 4.

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