audit_compliance

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

No annotations exist, so the description carries the full burden, and it does substantial work: it lists the five detection categories and the shape of the result (overall risk level, per-flag severities, monetization safety, publish-readiness). It stops short of stating that the operation is non-mutating and read-only, or noting constraints such as needing local file access or public YouTube URLs.

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 tight sentences: purpose first, detection categories second, return shape last. Every clause carries information and the front-loading is correct.

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 usefully compensates by describing return fields, and it enumerates detection scope. The remaining gap is the nested transcript input union (file vs. URL vs. raw text), which is a meaningful omission for a tool whose only required parameter is that object.

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?

Top-level schema coverage is 0% and the description only says 'a transcript and optional metadata,' which is essentially a restatement of the two parameter names. The critical detail — that transcript accepts three mutually exclusive input modes (local .srt/.vtt/.txt path, public YouTube URL, or min-50-char raw text) — is never surfaced in prose and must be excavated from nested schema properties.

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?

Uses a specific verb and resource ('Scan a transcript and optional metadata') plus an explicit goal ('compliance risks before publishing'), then enumerates the exact risk classes detected. This makes it unmistakably distinct from the sibling content-generation tools (generate_chapters, generate_seo_metadata, extract_shorts_hooks) without needing to name them.

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?

The phrase 'before publishing' establishes clear usage context as a pre-publish gate, which is the key timing signal an agent needs. It does not state when NOT to use it or name an alternative, but for this tool set there is no obvious competing option.

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