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

Annotations only cover the safety profile (not read-only, not destructive, not idempotent). The description adds substantial context beyond that: no credit cost, a 10-minute cut ceiling, per-account concurrency ('one account joins one set at a time'), audio mixing behavior (music looped to cut length and ducked under voice-over, narration laid at the named second), and the default 3s image hold.

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?

The core action is front-loaded in the first sentence and the remaining sentences each cover a distinct concern (workflow, audio mixing, cost, limits). It is dense but not padded; the audio-mixing sentence is long but earns its length given nested music/narration parameters.

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?

An output schema exists, so return values need no explanation, and the description covers cost, time limit, concurrency, and audio semantics for a 5-param nested tool. The remaining gap is the aspect_ratio parameter and the sources item type union, which are left entirely to the schema.

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 0%, so the description must carry the load, and it partially does: image_duration_seconds default (3s), narration start placement, and the music/ducking behavior implied by gain_db. But it never explains aspect_ratio's enum choices, the gain_db range/units, or the upload vs generation source discriminator in the sources array — the most structurally complex part of the schema.

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 opens with a specific verb, resource, and scope: 'Concatenate 2-20 images or clips, in the order given, into a single MP4 in the library.' It also carves out the single-clip-with-music exception and names the sibling tools (generate_clip, extract_video_frame) that feed it, so an agent can tell it apart from trim_video/loop_video without opening a schema.

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?

It supplies a concrete workflow ('generate each clip, carry the last frame into the next with extract_video_frame, then join them here') and states the conditions under which a single clip is valid. It does not explicitly contrast with other assembly/editing siblings (e.g. trim_video, render_storyboard) or say when not to use it, so it stops short of full routing guidance.

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