list_windows

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

With no annotations, the description carries the burden, and it does disclose scope: top-level windows only, plus the active modal window. However it says nothing about ordering, whether this is a safe read (implied by 'List'), snapshot behavior, or how hidden windows are treated.

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?

One tightly packed sentence: verb first, resource second, output fields parenthesized, and the extra modal-window behavior appended. No filler at all.

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?

No output schema exists, yet the description enumerates what each result entry contains, which is the main thing an agent needs. The remaining gap is the undocumented include_hidden flag and the absence of any behavioral/safety detail that annotations would normally supply.

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 0% and the single boolean include_hidden is never mentioned in the description, so an agent gets no guidance on how it affects the listing. Mitigating factor: one self-descriptive boolean with default false, so the omission is minor rather than crippling.

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?

States a specific verb+resource ('List top-level windows') and even enumerates the returned fields (objectName, title, class, geometry, modal) plus the active modal window. It doesn't explicitly contrast with siblings like dump_widgets or close_window, so the agent must infer the boundary.

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?

There is no statement of when to use this versus alternatives such as dump_widgets (which likely returns a deeper widget tree) or close_window. Usage is only implied by the resource name.

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