advanced_search

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: the form opens a NEW window, the Pattern field is set and Find clicked, the value is a UTF-16 fixed-width buffer bounded by the captured length, and there is no clean read-back so the list only narrows. It omits any error/permission or failure-mode context, keeping it short of exemplary.

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?

The single dense sentence packs in nested parentheticals and internal jargon ('GUID rebinder rebinding the dialog window (the answer_dialog / open_card machinery)'), making it hard to parse. Some content earns its place (default-field note, verification hint) but the structure is not front-loaded or clean.

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 UI-automation tool with an output schema (so return values need not be re-explained), the description covers the flow, side effects and verification adequately. Gaps remain around preconditions and the unexplained host/port/captured_value parameters, but nothing critical for invocation is missing.

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 6 parameters, so the description must compensate. It adds real meaning to value (re-targeted buffer, bounded by captured length), capture (the captured FieldSelector at «Код») and search_command (the default ДенамическийСписокИерархияНайти), but leaves host, port and captured_value unexplained.

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 opening clause states a specific verb and resource: filter a dynamic list via the «Расширенный поиск» dialog. However, the purpose is then buried under implementation jargon (GUID rebinder, answer_dialog/open_card machinery) and it never names its closest siblings (search_list, search_list / choose_from_list) to differentiate itself.

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: it describes the captured flow and that the search targets the dialog's default field (FieldSelector left at «Код»), plus a verification hint via capture_screenshot. There is no explicit when-to-use vs. the alternative list-search tools nor any stated preconditions (e.g., that the dialog must already be open/captured).

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