mac_find

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

Beyond the readOnly/idempotent annotations, the description discloses matching semantics (substring, case-insensitive unless exact:true), result caps (default 10, max 50), the fact that a new snapshot is taken and element_index refers to it, and the side effect of setting AXManualAccessibility on Electron/Chromium apps while deliberately never setting AXEnhancedUserInterface because it alters window behaviour. The NORACU_READ_ONLY=1 override is also spelled out.

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?

It is front-loaded with the match criteria and every clause carries information, but the single semicolon-chained paragraph crams defaults, side effects, and env-var caveats together, making it harder to scan than a short bulleted structure would be.

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 12-parameter tool with no output schema, the description covers what is returned (up to limit matches, each with an element_index tied to a fresh snapshot, plus the reported web_accessibility state). Only a minor gap remains: it does not say where element_index is consumed downstream (e.g. mac_click/mac_set_value).

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%, yet the prose explains nearly every one of the 12 parameters: what text matches (title or value), what id means (AXIdentifier), the semantics of exact, the limit default and maximum, the window selector forms (index, title, or window_id), and the surface values (window | menubar | app) with window as default. This compensates fully for the empty schema descriptions.

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: 'Search an app's accessibility tree for elements', and enumerates the match keys (role, title, value, text, id/AXIdentifier). That distinguishes it from siblings like mac_click, mac_get, or mac_window, which act on or enumerate windows rather than searching for elements.

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 context is implied rather than stated: the mention of window_id 'from mac_windows' and the web_accessibility behaviour 'like mac_ax_state' points at related tools, but there is no explicit when-to-use versus mac_screenshot or mac_ax_state, and no exclusions. An agent can infer this is the element-lookup step before clicking or typing, but must do the inference itself.

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