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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is clear. The description adds minimal behavioral context beyond stating that the tool returns field metadata; it does not describe response shape or pagination. With annotations carrying the burden, this is acceptable but not exceptional.

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 sentences with no waste. The first sentence states the tool's output and content; the second gives actionable usage guidance. The structure is front-loaded and easy to scan.

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 no-argument, read-only metadata tool, the description is complete: it says what is returned, what those fields include, and when to call it. The absence of an output schema is mitigated because the description already describes the return content.

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?

The tool has zero parameters and the schema is 100% covered by that fact. The description does not need to explain parameters, and it correctly implies the tool takes no arguments. Baseline for zero-parameter tools is appropriately high.

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 clearly states what the tool exposes: every field accepted by the screener, with type and description. It is distinct from siblings like screen_assets, which actually filters assets, and list_nl_screens, which lists saved natural-language screens.

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 description explicitly tells the agent when to call it: before building a filter rather than guessing field names. It does not name sibling alternatives explicitly, but the timing guidance is specific enough to prevent misuse.

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