Generate object masks for every video frame from point prompts, enabling targeted edits like background replacement or compositing.
SAM2: a series of PNG masks, one per video frame.
| 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, the description carries the full burden of behavioral disclosure, but it only reveals that the result is a series of PNG masks per video frame. It does not disclose side effects such as writing output files, overwriting existing files, required model/downloads, processing time, or whether it consumes all frames or a subset.
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 extremely shortched, which could be considered concise, but it is under-specified rather than efficient. One fragment is not enough to support a 6-parameter tool and provides no operational structure beyond a vague output statement.
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?
Given the tool's complexity, six parameters, zero schema coverage, no annotations, and no output schema, the description is far from complete. An agent lacks crucial context about input video paths, coordinate conventions for points, label semantics, blur/erosion effects, and the format/location of produced masks.
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 none of the six parameters are explained in the description. The description adds no meaning to input, output, points, labels, blur, or erosion, leaving the agent to guess at semantics and valid usage.
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 fragment 'SAM2: a series of PNG masks, one per video frame' conveys the output format and video scope, so it is not a tautology, but it never states the operation with a verb such as 'segments' or 'generates'. It partially distinguishes from image segmentation by mentioning video frames, but it does not clearly define what inputs are consumed or what processing occurs.
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?
The description provides no guidance on when to use this tool instead of closely related siblings such as sam2_segment_image, sam2_object_track, or sam2_propagate_mask. There is no mention of the intended use case, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.