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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes well beyond them: the non-obvious side effect that each poll feeds the idle watchdog and keeps the session alive, the 404 meaning, modelless vs deployed behavior (latestPrediction null), and warm-up confidence caveats with quality/artifact thresholds. These are behavioral traits an agent could not infer from structured fields.

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 core definition is front-loaded in the first clause, and every subsequent sentence adds a distinct operational fact (modelless mode, warm-up, quality thresholds, 404, watchdog). No sentence is filler or restates the name.

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 an output schema present, return values need not be re-described, and the description still covers the states an agent must handle: no-model sessions, warm-up, poor-signal thresholds, inactive-session 404, and the watchdog side effect. Nothing needed to invoke or interpret it 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 description coverage is 100% and both parameters are documented in the schema, so the schema carries the load. The description adds no extra semantics for session_id or window (e.g. valid ranges or cost of a large window), which is the expected baseline of 3.

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 names a specific verb (poll/read) and resource (live streaming-session telemetry) and enumerates exactly what is returned: latest prediction, recent window, signal quality metrics, indicators, running stats. That content spec is specific enough that an agent can distinguish it from stream.status or stream.start without opening a schema.

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 states clearly when to use it ('Poll this while a session runs'), the precondition that it works with or without a deployed model, and the failure condition ('404 => session not active in this backend'). It does not explicitly contrast itself with the sibling stream.status for session-level metadata, so the routing guidance is strong but not fully explicit.

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