app_click_menu

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

No annotations exist, so the description carries the whole burden and does so well: it discloses focus stealing, pointer movement and restoration, the may_steal_focus gate, retry-on-empty-level behavior, what counts as failure (a menu left open means no command ran), and the offered/first_read diagnostics. It stops short only of explicit safety or reversibility framing for arbitrary menu commands, which is a minor gap rather than a missing one.

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 purpose, then organized under scannable headings (PATH BY NAME, IT NEEDS THE FOREGROUND, THE MENU BAR IS PER EDITOR). Some passages, such as the internal task-number rationale and the DevExpress bar explanation, are longer than strictly needed, though they do justify the tool's existence.

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 complex, focus-stealing, arbitrary-command tool with a four-parameter schema that lacks field descriptions, everything an agent needs is present: path syntax, gating, context dependence, expected dialog verification, failure semantics, and diagnostics. The Returns section slightly duplicates the output schema but usefully explains what 'ok', 'offered', and 'retried' actually mean.

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 compensate and does: menu_path syntax is given with concrete examples, rules for accelerator markers and trailing ellipses, multi-level submenu handling, and the rationale for names over positions; may_steal_focus, list_only, and expect_dialog each get behavioral meaning beyond their bare boolean/string types, including how expect_dialog changes what 'ok' means.

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?

Opens with a specific verb+resource+mechanism: 'Invoke ANY Altium menu command by path, by driving the menu.' It immediately distinguishes itself from the closest sibling: 'Use this when app_run_menu will not do,' and explains the sibling's failure mode (reports success for commands it never invokes). An agent can pick between the two without opening either schema.

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?

Explicit when-to-use (app_run_menu is unreliable), when-not-by-default (gated behind may_steal_focus), prerequisites (focus the matching document first because the menu bar is per editor), and handoff (dialogs are read with app_list_open_dialogs). It also names the discovery path: list_only reports what the current editor context offers.

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