kalshi_stream_collect

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

With no annotations, the description carries the full burden. It discloses the one-shot nature, the connect-list-disconnect lifecycle, and that it returns messages. This is useful behavioral context. It does not mention authentication requirements, message format, or behavior when no messages arrive, but for a read-only stream capture the core behavior is well covered.

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 description is two sentences, immediately states the core function, and avoids any filler. It front-loads the verb and resource, then adds scope and behavioral nuance without bloat. Every sentence earns its place.

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 WebSocket stream tool with 4 parameters and no output schema, the description covers the essential context: what it captures, that it is one-shot, and the time-boxed nature. It does not detail parameter interactions (e.g., max_messages vs duration, required channels for orderbook_delta), but the schema partially covers this. Overall, it is sufficiently informative for an agent to understand the tool's role and basic usage.

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 only 50%; channels and market_tickers have descriptions, but max_messages and duration_seconds do not. The description adds only an indirect hint with 'for the window you ask for' (referring to duration) and 'few seconds.' It fails to explain the interplay between max_messages and duration_seconds, or which channels require market_tickers. This is a significant gap for a 4-parameter tool.

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 clearly states a specific action: 'Watch Kalshi's WebSocket feed... and return the messages that arrive.' It identifies the resource (WebSocket feed) and distinguishes itself from sibling REST tools by emphasizing real-time streaming and one-shot capture. The phrase 'not an ongoing subscription' further clarifies its unique scope.

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 provides a clear use case: 'Useful for seeing live order book changes, trades, or your own fills as they happen.' It also states when not to use it (for ongoing subscriptions), implying for persistent streaming you should look elsewhere. However, it does not explicitly name alternative tools like get_market_orderbook or get_trades for historical/snapshot needs, so some guidance is implicit rather than explicit.

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