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

Beyond the annotations (which only flag openWorld/non-idempotent/non-destructive), the description discloses quota consumption ('one of the account's 5 free preliminary checks per day'), expected latency (~1 minute), the ~40-second async threshold with status 'processing', and the shape of the result including a 20-point-wide preliminary score range and a link to the full report. That is exactly the operational context an agent needs to set user expectations and handle the async path.

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 purpose and required input are front-loaded in the first clause, followed by usage, then return/async/quota details in a logical order. It is a dense block rather than a scannable list, and the return-value enumeration could be trimmed, but every sentence carries information.

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 carries the full burden and does: it enumerates what comes back (20-point score range, 3-second hook checks, weak areas, measured problems like subtitles/loudness/safe zones, report link). It also covers the async fallback, quota, and latency, so an agent can call it and handle every outcome 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?

Schema description coverage is 100%, with enums and defaults documented inline (platform guessing, ISO country fallback to US, audience age bands, report language). The description only restates that scoring uses the given platform, market and audience age and that platform is inferred from the link, adding no syntax or fallback detail beyond the schema. Baseline 3 is appropriate.

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 states a specific verb and resource — starting a preliminary check of a short vertical video ad from a public link — and bounds the scope (up to 3 minutes, enumerated platforms, sized for a given platform/market/audience). It also differentiates itself from the sibling get_analysis by explaining that an unfinished run returns status 'processing' plus an analysis_id for that tool.

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 gives explicit trigger conditions: 'Use it when the user shares a link to a video ad and asks to watch, analyze, review, score or improve it.' It also points at get_analysis for continuation, but never explicitly says when to prefer upgrade_to_full_review over this preliminary check, nor states exclusions (e.g. non-video or horizontal ads).

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