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

Beyond the readOnly/openWorld annotations, the description discloses real operational traits: credit cost, that repeated requests may purchase data again, and that cache hits cost 0 credits and return 'cached': true with a cached_at timestamp. That is genuinely useful context the annotations do not carry, though the cost statements are internally inconsistent ('at least 10 Nexscope credits' versus '1 credit per request'), which muddies the pricing signal.

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?

The payload sentence is well front-loaded, but the remainder is pasted pricing/documentation boilerplate: an undifferentiated pricing line ('Twitch Clip API View Pricing Get Twitch clip 1 credit per request'), a markdown docs link, and a cache paragraph copied verbatim from the schema. The contradictory credit figures force the agent to guess which cost applies.

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 compensates well by enumerating the returned fields down to video qualities and signed playback URLs, and it covers cost and caching behavior. Missing only error/failure behavior and any note that the URL must be a clip rather than a channel or VOD link.

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% and both parameters are documented in the schema, including the enum for cache_max_age. The description's cache paragraph is a verbatim duplicate of the schema text, so it adds no meaning beyond structured fields; 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?

The first sentence names a specific verb and resource ('Fetches detailed data for a Twitch clip by URL') and enumerates the payload (slug, embedURL, viewCount, videoQualities with signed videoURL), which makes it clearly a clip-detail tool rather than a transcript or profile tool. It stops short of explicitly naming the nearest sibling (social_twitch_clip_transcript), so differentiation is inferential rather than stated.

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 URL' tells the agent the input must be a clip link, and the caching paragraph explains when a cached versus live result is returned. There is no explicit when-to-use/when-not-to-use guidance and no mention of the transcript sibling for agents that actually want spoken content.

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