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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real context beyond them: the image is read from memory, it is exactly what VNC viewers receive, and it is cheap enough for frequent polling. It does not discuss latency, size, or failure modes, but the added cost/source detail is genuinely useful.

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 tight sentences, front-loaded with what the tool returns, followed by cost/source context and the prerequisite note. No filler; each sentence carries distinct information.

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 read-only snapshot tool with full annotation coverage, the description supplies the return shape, the source of the image, the cost profile, and the prerequisite clarification. Nothing needed to invoke it correctly is missing, and no output schema is required for an image-returning tool.

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 100% for the single udid parameter, so the schema already documents it fully. The description adds no syntax, format, or meaning beyond what the schema provides, so the baseline 3 applies.

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 ('returns the current screen as an image') plus the return shape ({width, height} in points). It names one sibling (ios_vnc_open_hid) to clarify prerequisites, but does not distinguish itself from the many other screenshot siblings (ios_screenshot, ios_fast_screenshot, ios_mjpeg_screenshot, device_screenshot), which is the main clarity gap.

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?

'Cheap enough to call after every action' gives a concrete usage cadence, and 'Does not need ios_vnc_open_hid first' removes a prerequisite the agent might otherwise assume. It offers no explicit when-not or alternative-selection guidance against the other screenshot tools, so it stops short of 5.

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