Tracks a single object across video frames using SAM2 point prompts, outputting masks and a JSONL track with bounding boxes and centroids to enable object-aware editing workflows.
SAM2: masks plus a JSONL track (boxes and centroids) for one object.
| Name | Required | Description | Default |
|---|---|---|---|
| blur | No | ||
| input | Yes | ||
| labels | No | ||
| output | Yes | ||
| points | Yes | ||
| erosion | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It does state the expected outputs (masks and JSONL track), but it does not mention side effects, file writes, speed, failure modes, or processing lifetime, which is significant for a tracking tool.
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 description is very short and free of filler, and it front-loads the core output concept. However, it is closer to an under-specified fragment than a useful tool contract, and the brevity comes at the expense of essential context.
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 tool with six parameters, no output schema, and no annotations, the description is far too sparse. It does not explain the role of point prompts, labels, blur/erosion parameters, or what input/output paths mean, so an agent cannot confidently invoke this tool correctly.
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%, and the description adds no meaning to input, output, points, labels, blur, or erosion. Since the schema itself only provides types and constraints, an agent has no semantic basis for choosing correct parameter values.
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 clearly identifies the tool's output artifacts (masks plus a JSONL track with boxes and centroids) and narrows scope to a single object. It is not a tautology and is more informative than a bare name, though it lacks an explicit action verb and does not name sibling tools for contrast.
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?
No guidance is given on when to use this tool versus alternatives such as sam2_segment_video, sam2_propagate_mask, or sam2_refine_mask. The phrase 'for one object' weakly implies a single-object use case, but there is no explicit when-to-use or when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.