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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive, so the safety profile is covered. The description adds genuinely new behavior: a per-call price ($0.004 USDC on Base or Solana), the required X-PAYMENT header, and the X-Trial: 1 free-trial escape hatch — the kind of detail an agent cannot infer from structured fields.

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?

Two sentences, both front-loaded: what you get first, then how to pay for it. No filler, no restating the title beyond the payment qualifier.

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 and no annotations covering cost, the description rightly covers return fields and payment. But for a 4-param tool at 0% schema coverage, the unresolved q/query duplication and unexplained 'gl' leave an agent guessing at required inputs.

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% across 4 parameters with none required, so the description must compensate. It only clarifies 'num' indirectly via 'up to 20' and says nothing about 'gl' (presumably geo/language) or why both 'q' and 'query' exist — a real ambiguity for a caller.

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 resource and shape: 'Video results (title, url, channel, duration, date, thumbnail) for one query, up to 20.' The resource type alone separates it from image_search, news_search, and web_search, and the listed return fields tell an agent exactly what a call yields.

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 only implied by the resource name; there is no explicit 'use this instead of news_search when...' routing despite many sibling search tools. The payment/trial mechanics give practical call context, but the choice between this and sibling search tools is left to inference.

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