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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true. The description adds non-obvious behavior beyond them: that the session is removed from the idle watchdog so it cannot fire after an explicit stop. 'Always safe to call' is a mild tension with idempotentHint=false but reads as 'will not error', not a contradiction.

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?

Two short sentences, front-loaded with the core action and immediately followed by the safety note and side effect. No filler, though the watchdog sentence could arguably be tightened.

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?

An output schema exists so return values need not be explained, and annotations cover the destructive/read-only profile. For a single-parameter stop tool the description supplies enough, with only the absence of alternative-routing guidance as a gap.

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% with a single well-documented session_id, so the schema carries parameter meaning. The description adds nothing about the parameter beyond what the schema states, which is the expected baseline here.

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 (stop) and resource (streaming session) plus a secondary effect (disconnect the device). It is clearly distinguishable from siblings stream.start, stream.status, and stream.telemetry without opening any 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?

The parenthetical 'always safe to call' implies this can be invoked freely, but there is no explicit statement of when to use it versus stream.start or stream.status, nor any preconditions or when-not guidance. Usage is only implied by the obvious start/stop pairing.

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