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

Goes far beyond the annotations: cache window (5 minutes), latency (1-2 s typical, up to 40 s), exact price (USD 0.025, no free tier), billing behavior on unavailable/empty (uncharged 422) vs partial deliveries (charged), null-author behavior, and an explicit untrusted-data warning. This is precisely the context a caller cannot get from readOnlyHint=true.

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 what the tool returns, then constraints, then cost/latency, then the safety note — an effective ordering. It is dense and near-telegraphic ('partial deliveries charged.'), with a stray double period, but virtually every clause carries operational 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 an output schema present and 100% parameter coverage, the description fills the remaining gaps a caller needs: scope of the sample, sampling limits, cost, billing edge cases, latency tail, cache freshness, and prompt-injection caution. Nothing material is missing for correct invocation.

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 100%, so baseline is 3, but the description adds real meaning: include_authors=false yields author=null, likes are rounded/nullable, dates are relative, and the returned set is a partial sample capped at 50. That clarifies output-shape consequences of parameter choices rather than restating 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?

States a specific verb and resource ('Get public YouTube comments') and immediately narrows the scope to 'top-level' comments sampled up to 50, which distinguishes it from get_youtube_transcript (transcripts) and list_youtube_videos (video listings). An agent can route to it without opening the 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?

Usage is implied through concrete behavior (sort=top/newest, limit 1-50, include_authors=false for privacy), and the 422/uncharged note implies 'this may fail on empty videos'. But there is no explicit when-to-use vs sibling tools such as get_youtube_transcript, nor any exclusions, so it sits at minimum-viable guidance.

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