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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds behavioral context beyond this by noting that the list 'INCLUDING refusals' – a specific trait of what is returned – and that the items are 'previously compiled', implying they are historical saved screens. No contradiction with annotations.

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?

The description is two sentences with no filler. It leads with the core purpose (what is listed) and immediately adds the useful detail about refusals, then provides a practical use-case. Every word contributes to understanding the tool.

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 simple read-only list tool with one optional parameter and annotations covering safety, the description is largely complete. It explains the content and the purpose. The only gap is the lack of any mention of the limit parameter or the return format, but given the simplicity and the read-only nature, this is a minor omission; an agent could still correctly invoke the tool with just this description.

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 schema has a single parameter, limit, with zero description coverage. The description does not mention this parameter at all or explain how it affects results (e.g., limiting the number of screens returned). Since schema coverage is 0%, the description is responsible for compensating, but it fails to do so. The parameter name alone is insufficient for an agent to understand its semantics confidently.

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 states a clear, specific verb and resource: 'list natural-language screens'. It further specifies the content ('the English somebody wrote and the filter it compiled to, INCLUDING refusals'), which distinguishes it from sibling tools like screen_assets (which likely executes filters) and screener_fields (which lists available fields). The purpose is unmistakable.

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 provides a clear use case: 'Useful as worked examples of the screener's filter grammar before you write one.' This implies when to use it (when preparing to write a screen) and provides context for how it differs from executing a screen. However, it does not explicitly mention alternatives like screen_assets or screener_fields, nor does it state when not to use it, so it falls short of a 5.

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