pir_pick_window

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

With no annotations, the description carries the behavioral burden. It discloses the interactive prompt, the box overlay, Escape cancellation, and the follow behavior. It stops short of stating whether an existing region of the same name is overwritten or what the cancellation return looks like, but the core interaction is transparent.

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, front-loaded with the core user interaction, with no wasted or redundant wording. It adds essential behavioral detail without restating the tool name or schema.

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 human-in-the-loop picker, the description covers what the user sees, how to cancel, what happens after selection, and when to prefer it over the main sibling. It is slightly incomplete only in not describing return/cancel semantics or the required name parameter's role.

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 only 50% because the required 'name' property lacks a description. The tool description adds operational context but does not explicitly explain how 'name' maps to the region that follows the window, leaving that inference to the agent. The 'purpose' parameter is already handled by the schema description.

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 names a specific action ('Ask the person at the screen to click the window to watch'), the interaction mode (visible windows offered as boxes), and the outcome (the region follows that window). This clearly identifies the tool as a human-driven window picker and distinguishes it from region- or mask-based siblings.

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?

It explicitly states 'Prefer this over pir_define_window when a human is present,' giving a concrete routing condition and naming the alternative. This is sufficient for an agent to select this tool over the most similar sibling without opening another schema.

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