screen_elements

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), so the description is not the sole source of truth. It adds real behavioral value beyond them: the cost/precision trade-off versus screenshotting and what the returned elements consist of. It does not mention failure modes such as a missing or unreachable device.

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 compact sentences, no filler: the payload definition comes first and the routing hint second. Every clause carries 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?

An output schema exists, so return values need not be re-explained, and the description appropriately covers purpose and alternative selection. The only gap is device targeting via the undocumented 'serial' parameter.

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 one parameter ('serial') with 0% schema description coverage, and the description never mentions it or explains that an empty default means 'current/default device'. With an undocumented optional parameter, the description should compensate and does not.

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 resource ('each visible text or touchable element') and enumerates the returned fields (centre, type, id, state) in a single front-loaded clause. It also names the sibling tool it competes with (screenshot) and the axis of comparison, so an agent can pick it apart from the other read tools immediately.

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?

'Cheaper and more precise than a screenshot for tapping' gives a clear selection condition against a named alternative. It stops short of an explicit when-not (e.g. view this only when visual appearance or rendering matters), leaving the converse inference to the agent.

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