mac_windows

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description adds genuinely non-obvious context: the exact shape of each returned record, inclusion of display info, and the fallback that titles come from accessibility when Screen Recording is not granted. That permission-dependent behavior is real value beyond the structured fields.

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 dense paragraph with the core action and return fields front-loaded, then the permission caveat and the parameter note. Every clause carries information, though the telegraphic colon-list style is slightly terse for a first-time reader.

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?

There is no output schema, so the description's enumeration of returned fields is exactly what is needed for a zero-required-parameter list tool. Remaining gaps are minor: app-matching semantics and whether results are z-ordered or span multiple Spaces are not stated.

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 description coverage is 0%, so the description must carry the parameters, and it does explain both: include_offscreen expands results to hidden/minimized windows, and app filters by app name. It stops short of specifying whether app matching is exact, substring, bundle identifier, or display name, which matters for a 0%-documented schema.

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 opens with a specific verb+resource: 'List on-screen windows', then enumerates the returned fields (id/CGWindowID, app, pid, title, bounds, displays). It is clearly a window-enumeration read tool, distinguishable from mac_window or mac_apps, though it never explicitly contrasts itself with those siblings by name.

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?

Usage is only implied — an agent infers this is the tool for discovering windows before acting on one. The one conditional given ('include_offscreen:true adds hidden and minimized ones') is a parameter behavior rather than a when-to-use rule, and there is no guidance on when to prefer mac_window, mac_find, or mac_apps instead.

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