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

Goes well past the readOnly/destructive annotations: snapshotId is valid for only one action, content outside the window's visible area is not listed, password fields render as (hidden), app text is untrusted content rather than instructions, and the call requires ui permission plus macOS Accessibility permission. These are exactly the behavioral traits an agent needs and cannot get from 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?

Front-loaded with the core purpose and the return shape, and every clause adds real information (scope, ids, snapshotId lifetime, permissions). It is delivered as one dense multi-clause block rather than separated points, which slightly hurts scanability, but there is little outright waste.

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 describes the return shape, its limits (visible area only), and the permission prerequisites, so an agent can call it correctly. The remaining gap is operational: truncation via maxElements and the meaning of the window index are never addressed.

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 only 29%, so the description must carry the load. It explains 'app' (name or bundle id, omit for front), 'menu' (one menu name includes its submenus), and implies 'scope', but says nothing about 'window' (which window index), 'maxElements' (truncation behaviour), 'deviceId', or 'workSessionId'. Partial compensation for a low-coverage 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?

States a specific verb and resource ('Read a native Mac app as a screen reader does') and enumerates exactly what is returned: controls, text, ids, roles, names, values, operations, and a snapshotId. It also distinguishes itself from the sibling action tools by naming the operations (press, type, select...) as the app_ tools that consume this snapshot.

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?

Gives concrete operating context: omit 'app' for the front app, use scope=menus to walk the menu bar, name one menu to include its submenus, and that it works on non-front apps listed by runningApps. It stops short of explicitly saying 'call this first to obtain the snapshotId before any app_press/app_type', which is only implied by 'valid for one action'.

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