Screen relay (internal)

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

The description adds one genuinely useful behavioral trait beyond the annotations: this is a long poll, so it blocks/waits rather than returning immediately. Annotations already declare non-destructive and closed-world (openWorldHint=false), so the safety profile is covered, but nothing is said about timeout, retry, or payload shape.

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?

A single front-loaded sentence that discharges the internal/app-only qualifier first and wastes no words. Its brevity is efficient rather than padded, though the size is small relative to the tool's actual complexity.

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 tool with 8 parameters, a nested object, and no output schema, the description is far too thin; the job/status field semantics are undocumented anywhere. Being internal lowers the bar somewhat, but an agent still lacks what it needs to interpret or drive the poll 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?

Eight parameters are documented at 0% schema coverage, and the description explains none of them. 'The open app's' faintly gestures at the app/session scope, but the opaque fields (born, done, touched, ping, display, visible) and the nested 'done' object are left entirely unexplained.

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?

The description gives a verb-ish action ('long poll') and a resource ('screen jobs') scoped to 'the open app', which separates it from siblings like screen_read and screen_act. However, 'screen jobs' is never defined, so an agent cannot form a concrete picture of what is being polled or returned.

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 'Internal (app-only)' signals who should invoke it and implies external callers should stay away, which is meaningful routing guidance. But it names no alternative and states no positive condition for use, so the when-to-use vs siblings is only implied.

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