list_app_windows

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

With no annotations, the description must carry the burden of behavioral disclosure. It states the tool lists 'visible' windows, implies case-insensitive filtering, and clarifies the empty-filter behavior. However, it does not disclose output format, ordering, potential latency, or any side effects. Since the operation is read-only, that is likely safe, but the description lacks explicit transparency about what happens after invocation. Some behavior is disclosed, so a 3 is appropriate.

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 extremely concise, with the purpose and usage stated in the first two sentences. The Args section is minimal and directly explains the parameter. No unnecessary words or redundancy. Every sentence serves a purpose, making it efficient for an agent to parse.

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?

The tool is simple with one optional parameter, and the description covers the main use case (finding window titles for screenshots) and the filter behavior. An output schema exists, so return values are not required in the description. It does not mention edge cases like minimized windows, but 'visible' is defined. Overall, it is complete enough for an agent to call correctly without further investigation.

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 provides only a type and default for filter_text with 0% description coverage. The description compensates by explaining the parameter's purpose: 'Optional text to filter window titles (case-insensitive). Leave empty to list all visible windows.' This adds meaning beyond the schema, clarifying the filtering behavior and the default action. It does not specify whether filtering is substring or exact match, but it is sufficient for most agents.

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 the verb 'List' and the resource 'visible application windows on the desktop', and provides a specific use case (finding a window title before a screenshot). It distinguishes itself from sibling screenshot_app by explicitly referencing it as the follow-up action. The filter parameter is also mentioned, making the purpose unambiguous.

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 gives explicit guidance on when to use the tool: 'Use this to find the exact title of a window before taking a screenshot with screenshot_app.' It also explains the filter usage and default behavior. It does not explicitly mention when not to use it or alternatives, but the primary alternative (screenshot_app) is referenced, providing clear context for the typical workflow.

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