Embed invisible DCT-domain watermark into an image. Encodes a text payload into luminance channel frequency coefficients. Survives light compression. FREE. (FREE)
| Name | Required | Description | Default |
|---|---|---|---|
| image | Yes | Base64-encoded PNG/JPEG image | |
| payload | Yes | Text payload to embed (max 256 chars) | |
| strength | No | Embedding strength (0.1-1.0, higher = more robust but more visible) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, but the description indicates a write operation ('Embed invisible... watermark into an image'). This is a direct contradiction; the tool modifies the image and is not read-only. No additional behavioral context is provided to resolve this discrepancy.
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 short but contains redundant text: 'FREE. (FREE)' appears at the end, which adds no value and looks like an error. The first sentence front-loads the purpose, but the repetition and lack of structured info about outputs detract from conciseness.
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?
With no output schema, the description should explain what the tool returns (e.g., the watermarked image) but does not. It does mention robustness ('Survives light compression') and technical detail, but the annotation contradiction and missing return-value information leave the description incomplete for a tool that modifies an image.
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 100%, so the baseline is 3. The description adds technical context (e.g., luminance channel, DCT-domain) that enriches understanding of the payload and strength parameters, but it does not provide significant new parameter-level details beyond the schema.
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 embeds an invisible DCT-domain watermark into an image and encodes a text payload. This is a specific verb+resource+method, and it distinguishes from sibling tools like watermark_detect (which detects watermarks).
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 implies a use case via 'Survives light compression,' suggesting the tool is suitable when light compression robustness is needed. However, it does not explicitly state when to use this tool versus alternatives like watermark_detect, nor does it provide any exclusions or prerequisites.
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.
Most tools have distinct purposes, but there is some overlap between get_artwork and get_artwork_oracle, which both retrieve artwork metadata with different detail levels, potentially causing confusion. Other tools like enrich_metadata and infuse_metadata also have related but distinct functions, but descriptions help clarify differences.
Tool names generally follow a consistent verb_noun pattern (e.g., check_balance, delete_asset, resize_image), with minor deviations like mockup_image (noun_verb) and get_artwork_oracle (longer compound name). Overall, the naming is readable and predictable, though not perfectly uniform.
With 27 tools, the count is borderline high for a single server, as it covers a broad range of functionalities from artwork retrieval to image processing and compliance. While each tool seems useful, the scope feels heavy and could overwhelm agents, suggesting it might be better split into more focused servers.
The tool set provides comprehensive coverage for digital asset management, artwork analysis, and image processing, including CRUD operations (save_asset, get_asset, list_assets, delete_asset), metadata enrichment, compliance, and various image utilities. No obvious gaps are present for the stated domain.