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

Annotations cover only the safety profile (readOnly=false, idempotent=false, destructive=false); the description adds substantial behavior the annotations cannot: the self-authenticating ~5-minute link window, 30-minute page lifetime with reconnect after a drop, per-user audience restriction ('share with care'), the view staying open while anyone is connected, and localVncUrl being omitted when the device is attached to another host.

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?

Front-loaded with the primary action and the key instruction ('GIVE THE USER viewerUrl') before the return-shape and lifetime details. It is dense and the authentication window is stated twice in slightly different forms, but nearly every sentence carries distinct, decision-relevant information about the three URLs.

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, the description must explain return values and does so field by field (viewerUrl, websocketUrl, localVncUrl, width/height, expiry fields), plus rotation behavior and lifecycle. Nothing needed to call and manage this session-opening tool 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?

There is a single parameter (udid) at 100% schema description coverage, so the schema already documents it fully. The description adds no parameter-level detail beyond what the schema provides, which is the baseline-3 case for a well-covered single-param tool.

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 ('Open a live, interactive view of an iOS device for the USER') with the human-facing intent spelled out. It explicitly distinguishes itself from siblings by naming ios_vnc_snapshot_hid for agent-side viewing and ios_vnc_close_hid for release, so an agent can pick correctly without opening schemas.

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?

Explicit routing: 'To LOOK at the screen yourself, use ios_vnc_snapshot_hid instead' and 'call ios_vnc_close_hid when you no longer need it held.' It also states who the view is for (the user currently holding this device) and the condition for using the raw websocketUrl (a client bringing its own viewer).

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