Record the camera's current aim under a label so go_to can return to that exact view later.
Remember the current direction under a name, for later use.
Pan is an absolute axis whose meaning depends on where the camera is standing, so
"point at the door" is unanswerable without recording it once. Call this with the camera
already pointed where you want, and the label becomes usable with go_to.
| Name | Required | Description | Default |
|---|---|---|---|
| label | Yes |
Changes observed during successful MCP inspections.
v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden but only partially fulfills it. It usefully explains the rationale (pan is an absolute axis, so a label must be recorded once) and that the label is later consumed by go_to, but it says nothing about whether an existing label is overwritten, whether labels persist across sessions, or what the call returns.
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 core action is front-loaded in the first sentence, and the second paragraph's explanation of the pan/absolute-axis problem fits in two lines. Slightly verbose in its justification, but every sentence supports the reader's decision to call it.
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 single-parameter tool with no output schema or annotations, the description covers purpose, precondition, and consumer, which is largely sufficient. It remains incomplete on label lifecycle semantics (overwrite behavior, persistence) that an agent would need to call it safely.
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?
One parameter with 0% schema description coverage, so the description must compensate. It implies the 'label' is a reusable name for the recorded direction, but adds no constraints on format, uniqueness, or whether reusing a name replaces a prior recording.
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 ('Remember the current direction under a name'), which is far more informative than the cryptic name 'aim_learn'. It also names the sibling that consumes the result ('go_to'), though it does not distinguish itself from other state-recording siblings like mark_view or check_view.
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?
'Call this with the camera already pointed where you want' gives an explicit precondition for invoking the tool, and 'the label becomes usable with go_to' routes the agent to the correct follow-up tool. No when-not guidance or contrast with the other camera-state siblings is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.