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

Annotations already cover safety (readOnly, idempotent, non-destructive), so the description focuses on what they cannot express: no API key is required, the response includes plan and cost information, and the connection must be held by a long-lived server, not by the MCP call. That is genuinely additive context for a documentation-style tool; only the response shape is left vague.

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 short sentences, front-loaded with the key fact (no key needed) followed by what is returned and the execution caveat. No filler or repetition; the slightly telegraphic phrasing costs no clarity.

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 one-parameter, no-output-schema lookup, the description covers both what the tool produces (URL, plan, cost, steps) and the operational constraint that streaming must happen outside the MCP call. Nothing essential to calling it correctly is missing.

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 0% and the single enum parameter is undocumented in the schema, so the description must compensate. It does so by naming both accepted values in prose — the Pick6 change stream and the native sportsbook WebSocket — giving the agent enough to pick the right enum without guessing.

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 makes clear this returns connection details (exact URL, plan, cost, steps) for two live feeds rather than data itself, which separates it from snapshot siblings like get_pick6_stream_snapshot. It never states an explicit verb such as 'returns' or 'documents', but the resource and scope are unambiguous.

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?

"An MCP call cannot hold them open" and "which a long-lived server connects to" effectively tell the agent when this tool is the right route: when the caller needs a persistent stream rather than a one-off read. It does not explicitly name the snapshot/get_* alternatives as the fallback, so the exclusion is implied rather than stated.

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