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

Goes well beyond readOnlyHint/openWorldHint: discloses that this is inference over prose, that YouTube publishes no structured sponsor data, that every signal carries a source line and a confidence, that it is experimental, and that it costs 1 credit. That is exactly the context annotations cannot carry.

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?

Four short sentences, front-loaded with what is returned, followed by why evidence/confidence matter, then the experimental caveat and cost. Zero filler; each sentence changes how the agent treats the result.

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 carries the return-value burden and does so — naming the signal fields and their accompanying evidence/confidence. Combined with the credit cost and experimental status, an agent has everything needed to call it and interpret the result responsibly.

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 50%: `url` is documented as URL-or-11-char-id, while `cache_max_age` is undocumented in both schema and description. The description adds no parameter-level detail, so it neither compensates for the gap nor is required to for the documented required param. Baseline 3.

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?

Specific: it enumerates the resource (brands, promo codes, affiliate links, YouTube's paid-promotion disclosure) and the source (a video's description prose). An agent can tell it apart from youtube_video or youtube_transcript without opening the schema. It stops short of explicitly naming which sibling to use instead when only raw metadata is wanted.

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?

Gives a real operational rule — check `evidence` before acting on `low` confidence — which is genuine when-to-use guidance for the output. However, it never states when to pick this over youtube_video (metadata) or youtube_transcript, and no exclusion is given. Usage is implied rather than routed.

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