Embed an invisible Resemble provenance watermark into media (audio-first) and return the watermarked media URL. strength 0.0-1.0 (image/video only).
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| strength | No | ||
| custom_message | No | ||
| max_wait_seconds | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose all behavioral traits. It mentions embedding and returning a URL, but omits crucial details: whether the original is modified, what happens to existing watermarks, synchronous vs asynchronous behavior, authentication needs, or error handling. The 'audio-first' qualifier is vague.
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 concise (one sentence plus parenthetical) and front-loaded with purpose. However, it sacrifices completeness, missing key parameter details and behavioral notes, which makes it less effective.
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 4 parameters, no annotations, and no output schema, the description is insufficient. It does not explain the return type, async behavior (implied by max_wait_seconds), limitations, or parameter interactions. The 'audio-first' note is unclear.
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?
Only one parameter (strength) is partially described with a range and scope constraint. Three parameters (url, custom_message, max_wait_seconds) receive no explanation. Given 0% schema description coverage, the description should explain all parameters but fails to do so.
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 states the tool's function: embedding an invisible Resemble provenance watermark into media, with 'audio-first' specified and a note about strength for image/video. It distinguishes from sibling tools like detect_watermark or trace_audio_source.
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 explicit guidance on when to use this tool versus alternatives. While implied for embedding watermarks, no exclusions or comparisons to siblings are provided, leaving the agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: media analysis, watermarking, deepfake detection, watermark detection, detection retrieval, question answering about detections, and audio source tracing. No two tools overlap in functionality.
Tool names consistently use lowercase with underscores and a verb_noun pattern, though 'ask_about_detection' is slightly longer and deviates from the direct verb_noun structure (e.g., 'detect_deepfake'). Overall, the pattern is predictable.
Seven tools effectively cover the core capabilities of the Resemble AI server (media analysis, deepfake detection, watermarking, source tracing, and result queries). The count feels well-scoped for the domain.
The tool set covers the main workflows: detection, analysis, watermarking, and retrieval. Minor gaps exist, such as lacking a tool to list all detections or delete media/watermark, but the essential operations are present.