save_anchorRemember a tap target from a look node or raw normalized x,y coordinates, enabling agents to reuse the exact screen location in later steps.
Remember a tap target. From a look node (stores selector + point) or raw normalized x,y.
| Name | Required | Description | Default |
|---|---|---|---|
| x | No | ||
| y | No | ||
| name | Yes | ||
| node | No | ||
| notes | No | ||
| device | No | ||
| map_name | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. 'Remember' implies persistence, but it never states whether saving under an existing name overwrites, whether the anchor is scoped per map/device, or whether any prerequisites apply. For a write tool with zero annotation coverage, this is a real gap.
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?
Two tight sentences with the core action front-loaded and the input variants following. No filler, though the terseness contributes to the coverage gaps rather than being purely economical.
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?
An output schema exists so return values need not be described, but for a 7-parameter mutation tool with no annotations and 0% schema coverage, the description is too thin. Missing are the map_name scoping semantics, overwrite behavior, and how this connects to `tap_anchor`/`look` in the workflow.
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. It touches x, y (as 'normalized'), and node, but leaves map_name, name, notes, and device entirely unexplained, including the required map_name scope. It covers only part of the surface it needs to.
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 states a specific verb ('remember') and resource ('tap target'), and clarifies the two source forms: a `look` node or raw normalized x,y. That is enough for an agent to understand it persists a tappable location. It stops short of distinguishing itself from siblings like `tap_anchor` (which presumably consumes what this saves).
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?
It implies two usage modes ('From a `look` node ... or raw normalized x,y'), which is useful context for how to call it. But there is no explicit when-to-use guidance, no statement of the relationship to `tap_anchor`, and no mention that a map must already exist via `list_maps`.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.