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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description still adds real behavioral context: it enumerates the measured signals, explains that hook_score is a 0-100 rollup of exactly those signals, promises suggested edits, documents alias normalization, and warns that every figure describes only the supplied text — an epistemic scope statement the schema and annotations cannot convey.

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?

Front-loaded with the core action and the outcome disclaimer placed last where it belongs. The signal enumeration in the second paragraph partially duplicates what an output schema already exposes, and the 'rollup of exactly those signals' phrasing is a touch redundant, but nothing is padding.

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 an output schema present and annotations covering safety, the remaining burden is scope and input expectations; the description handles scope thoroughly (text-only, no real-world outcomes) and platform aliasing. The one thing an agent could still get wrong — what constitutes valid transcript_text — is unaddressed.

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 does for target_platform, naming the canonical values and explaining that `reels`/`shorts` normalize and are echoed back in the result, which is information present nowhere in the schema. However, the required transcript_text parameter is never characterized (expected format, whether timestamps or markup belong in it), leaving a genuine gap.

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: measures what the opening of a short-video transcript does, returning named signals plus a 0-100 hook_score. It also draws an explicit boundary ('does not estimate reach, views, retention or virality') that prevents confusion with an analytics tool, and no sibling in the list overlaps in purpose.

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 when-not is explicit and strong: the tool never estimates reach, views, retention or virality, and 'Read `signals` to see what moved the score' tells the agent how to interpret results. What's missing is a positive when-to-use cue (e.g., before publishing a script) or a named alternative, so it stops short of the 5 bar.

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