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

Annotations only cover the safety profile (readOnly, openWorld, idempotent, non-destructive), and the description goes well beyond them: 15-minute caching, no captions or media, partial results billed while empty/unavailable searches are free, 1-2s typical / 15s worst-case latency, and a prompt-injection warning about treating returned page text as untrusted data. These are exactly the behavioral traits an agent cannot get 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?

Purpose and the 20-video cap are front-loaded, and nearly every clause carries information (cache, cost model, latency, trust warning). It is dense and somewhat run-on, with niche details like relative publication labels, but little is genuinely wasted.

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, the description is not obliged to explain return values, and it still covers the things that matter for correct invocation: scope limits, caching, cost/billing semantics, latency budget, and an untrusted-data warning. Nothing an agent needs to call this safely and predictably is missing.

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 both parameters are already fully documented in the schema (limit 1-20 one page only; query sent to YouTube). The description restates the cap ('up to 20 videos') but adds no syntax, format, or edge-case guidance beyond what the schema provides, so the baseline 3 applies.

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 ('Search public YouTube videos') plus the return type ('public YouTube video metadata for a query, up to 20 videos'). It is clear on its own, but it never distinguishes itself from the sibling 'list_youtube_videos' or 'get_youtube_transcript', leaving the agent to infer the distinction from the names alone.

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 verb 'search' versus the sibling 'list_youtube_videos'; there is no explicit when-to-use, when-not-to-use, or named alternative. The description does add operational context (cache window, latency, cost) that helps an agent decide whether it can afford the call, but not which tool to pick.

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