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

Annotations only declare the safe-read profile; the description adds substantial context beyond them: 404 means the session is not active, low confidence is expected during filter/ASR warm-up, quality<0.5 or high artifactProbability signals a poor signal, and each poll feeds the idle watchdog keeping a watched session alive. These are non-obvious operational behaviors 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?

Purpose is front-loaded in the first clause, and every subsequent sentence carries distinct operational value (routing, thresholds, error semantics, watchdog). It is a dense single block rather than being visibly chunked, which slightly hurts scannability but there is no filler.

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?

Output schema exists, so return values need not be explained, and annotations cover safety. The description still supplies the operationally critical context (prerequisites, error meaning, warm-up caveats, watchdog side effect), leaving nothing an agent needs in order to call it correctly.

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 already documented in the schema, so the baseline is 3. The description clarifies the output semantics ('recent window', 'latest prediction') but adds no syntax or format detail about the window parameter beyond the schema.

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?

States a specific verb and resource ('Live snapshot of a streaming session') and enumerates what the snapshot contains: latest prediction, recent window, signal quality metrics, indicators, running stats. It explicitly distinguishes itself from the sibling stream.status by naming the condition that routes to each.

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?

Gives explicit when-to-use ('Poll this while a session runs'), an explicit when-not ('modelless hardware streams have no telemetry — use stream.status for those'), and a prerequisite ('requires a DEPLOYED model session'). The alternative sibling is named with the selecting condition.

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