ui_key_sequence

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

Annotations carry almost nothing (only openWorldHint=false), so the description bears the burden and does disclose useful behavior: the accepted NUMPAD/NUMLOCK key vocabulary, that NUMLOCK toggles rather than sets a lock state, and that physical delivery needs the FlaUI backend. It is silent on the post-conditions that matter for a key-injection tool — whether modifiers stay held afterwards (cf. ui_release_modifiers/ui_get_held_modifiers), whether the target is focused first, and what "cleanup evidence" actually contains.

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 action, which is good, but the second half sprawls into a long menu-specific anecdote about harness observations vs. product defects that crowds out more broadly useful information. The key vocabulary block is justified; the MENU guidance is over-weighted.

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 7-parameter input-injection tool with no output schema and near-zero schema documentation, the description leaves the caller unable to construct a valid target argument or predict the returned evidence. The FlaUI-backend note is the only hint that delivery can fail; failure modes and return shape go unexplained.

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% across 7 parameters, so the description must compensate — and it only covers `keys` (with a valuable enum-like key list). The five target-selection parameters (name, xpath, root_id, control_type, automation_id) and the required `modifiers` array are never explained, including whether they are mutually exclusive or how an element is resolved.

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 concrete verb+resource ("Send keys while holding modifiers") plus an unusual side effect ("report cleanup evidence"). The modifier-holding aspect implicitly separates it from ui_send_keys/ui_send_keys_focused, but those siblings are never named, so the agent must infer the boundary from the phrasing rather than being told.

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 real usage guidance, but only for one narrow scenario: the WPF MenuItem workflow (scope ENTER to the parent, rediscover the popup child, invoke via ui_invoke, don't add a fixture-specific handler, use pre/post oracles). Nothing says when to pick this over ui_send_keys, ui_send_keys_focused, ui_send_keys_batch, or ui_hold_modifiers, which is the more common selection problem.

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