window_set_focus

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

With no annotations provided, the description fully covers behavioral traits: UI-affecting, changes visible window state, no data cache invalidation, return structure, error types (OF_WINDOW_UNAVAILABLE, OF_NOT_FOUND), and side effects. It also warns headless agents should not fire this, providing complete transparency.

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?

All sentences are information-dense and purposeful. Well-structured: purpose first, then UI warning, usage guidance, alternatives, parameter detail, return value, errors, side effects, examples. No redundant text; every part earns its place under 10 sentences.

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?

Given the complexity of a UI-affecting tool without an output schema, the description is complete. It covers purpose, usage boundaries, parameter semantics, return format, error conditions, and side effects. No gaps remain for an agent to safely use it.

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?

Schema coverage is 100% for the single parameter, but description adds significant meaning: explains that containerId can be a ProjectId or FolderId to set focus, or null to clear. Includes two concrete examples (prj123, null) and clarifies the effect on return value. This far exceeds basic schema documentation.

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?

Description clearly states it sets/clears the focus container (project/folder) on the front OmniFocus window. It contrasts with siblings like task_list and perspective_evaluate by explicitly stating not to use for filtering data, and notes that headless agents should avoid it. This makes the purpose distinct and clear.

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?

Provides explicit when-to-use: when user says 'focus on this project' or for guided flows. Also gives when-not-to-use: headless agents and for filtering task data. Points to specific alternatives (task_list with projectId, perspective_evaluate) that work without affecting UI.

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