stream_realtime

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

No annotations are provided, so the description carries full responsibility for disclosing behavioral traits. It reveals that the tool is 'polling-based' and returns 'recent data', which are useful but minimal. It fails to disclose what data fields or structure the response contains, whether there are any side effects (like opening a persistent connection), rate limits, or authentication requirements. The agent is left with significant uncertainty about how to handle the response.

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 a single, front-loaded sentence that conveys both the purpose and a key behavioral trait (polling-based, recent data). It contains no filler or redundant information. Every word contributes to the agent's understanding, making it highly concise and well-structured.

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?

The tool has no output schema and no annotations, so the description must compensate by explaining what the stream returns and how it fits with the sibling tools. It does not specify whether the stream returns trades, quotes, order books, or a combination, nor does it clarify the relationship to the get_* snapshot tools. With 11 siblings, the lack of differentiation and response format makes the description incomplete.

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?

The input schema covers all parameters (exchange, instrument, stream_time) with descriptions, achieving 100% coverage. The description adds no extra semantic detail about these parameters, so the baseline of 3 is appropriate. The schema already provides the necessary meaning for each parameter.

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 states a clear action ('Get') and resource ('real-time market data stream'), and adds the qualifiers 'polling-based' and 'returns recent data'. However, it does not specify what type of data (e.g., trades, order books) the stream contains, which would help distinguish it from the sibling get_* tools. The phrase 'market data stream' is broad but still conveys a distinct purpose compared to snapshot or historical data endpoints.

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?

The description implies usage for real-time or recent data via 'polling-based' and 'returns recent data', suggesting this tool is for repeated polling rather than historical queries. It does not explicitly mention when to use this instead of sibling tools like get_trades or get_orderbooks, nor does it mention any exclusions or alternatives. The guidance is embedded but not explicit.

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