Erase unwanted objects from video frames spatially: SAM2 segments the target from point prompts, OpenCV Telea fills the region per frame, with silent output.
SAM2 + OpenCV Telea: spatial erasure. No generative model, and no guaranteed temporal consistency. Silent video.
| 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 and does disclose several behavioral traits: the result is non-generative, lacks temporal consistency, and is a silent video. It does not disclose side effects such as whether the output file is overwritten, how input audio is handled beyond silence, or whether any data is destroyed.
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 front-loads the algorithm and key caveats with no filler; every phrase contributes information. The telegraphic fragments, especially 'Silent video,' are somewhat terse and ambiguous, but the structure is efficient and not redundant.
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?
The tool has six parameters and no annotations or output schema, yet the description provides almost no parameter documentation, input/output conventions, or side-effect information. The few caveats are useful, but the definition is not sufficient for an agent to reliably construct a complete call without external domain knowledge.
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 never names any of the six parameters. The mention of SAM2 indirectly hints that 'points' and 'labels' may be segmentation prompts, and OpenCV Telea hints at the inpainting approach, but blur, erosion, input/output path semantics, and label meaning are left 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 description identifies the core operation as 'spatial erasure' and names the composing methods (SAM2 + OpenCV Telea), which signals an object-removal/inpainting tool. It also distinguishes itself from generative alternatives by stating 'No generative model' and 'no guaranteed temporal consistency.' However, it never explicitly says it takes video plus point prompts and produces an inpainted video file.
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 stated limitations implicitly tell an agent when this tool is appropriate: use it for simple spatial erasure when generative content, temporal coherence, or retained audio are not required. It does not explicitly name sibling alternatives or provide concrete when-to-use/when-not-to-use conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.