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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real context: the response is connection documentation and plan-scoped limits, not market data, and the tool degrades into a discovery listing when dataset is omitted. Plan-tier dependence is noted but not explained.

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?

Three sentences, front-loaded with what is returned followed by the negative scoping clause and the no-dataset fallback. Dense and nearly waste-free, though the telegraphic phrasing ('Never the stream itself.', 'With no dataset, lists...') reads as clipped fragments.

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 and only 4 optional parameters, the description carries the burden well by enumerating the return contents and the dataset-absent behavior. It omits auth requirements and how plan limits are surfaced, which matters somewhat for a connection-documentation tool.

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 only 25%, so the description must compensate, and it does: it explains that dataset, exchange, interval and symbols together form the subscribe frame, and that omitting dataset switches to a listing mode. The 19 dataset enum values remain unexplained, but the sibling describe_dataset plausibly covers that gap.

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 precisely what the tool returns: a WebSocket URL, a subscribe frame for a dataset/exchange/interval/symbol combination, plan limits, and a Python client. 'Never the stream itself' sharply separates it from sibling data tools like fetch and get_data. It stops short of naming a sibling outright, so it is a strong 4 rather than a 5.

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 a concrete usage rule: with no dataset, the tool lists available streams and the plans that include them, which tells the agent how to use it for discovery. 'Never the stream itself' functions as an implicit exclusion steering the agent to fetch/get_data for actual data. No explicit when-not beyond that.

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