Kick

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

Annotations already establish readOnly, idempotent, openWorld, non-destructive, so the safety profile is covered. Beyond that the description adds genuinely non-obvious behavior: per-resource credit costs, that the result reports credits charged and remaining, that failures are free, and the 0-credit cached-copy option. The only omission is any hint of what a success payload looks like, which matters somewhat without an output schema.

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 the call pattern, then pagination and caching rules, then a compact bulleted resource list with costs. Nearly every sentence carries operational information. The one wasted element is the opening claim about 'posts and videos', which describes capability the enum does not offer.

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?

For a generic resource-dispatch fetch tool with no output schema, the description covers selection, argument routing, escalation to `describe`, pagination, caching, and cost accounting. An agent can invoke it correctly and predict the credit consequences without further reading.

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, and the description earns more by tying cost semantics to specific resources and by naming the resource-scoped optional arguments (`allow_long_transcription`, `ai_fallback`) that live inside `params` and therefore appear nowhere in the top-level schema. The tiered transcription pricing (1 credit to 2 minutes, then 5 per started minute of the whole video) is meaningful added meaning.

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 description opens by naming the platform and data type (Kick transcripts, posts, videos) and then enumerates the concrete resources (clip, clip.transcript) with what each returns. That is enough for an agent to separate it from the youtube/tiktok/twitch siblings. Minor flaw: the preamble advertises 'posts and videos' while the enum only exposes clips and transcripts, so the stated scope overpromises slightly.

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?

It gives explicit invocation mechanics: choose a `resource`, pass that resource's parameters as top-level arguments, put extras in `params`, and call `describe` for types and allowed values. It also explains pagination (pass the returned `cursor` back unchanged) and the free-cache path via `max_age_days`. It does not say when to prefer this over `get_transcript`, which is the one remaining routing gap given that sibling exists.

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