Tanod MCP server

imagepeek: add a text watermark to an image

image_watermark

Idempotent

Add a text watermark to an image at one of nine positions or tiled across it, with adjustable opacity, color, font size, and angle. Outputs the watermarked image.

Instructions

imagepeek: Add a text watermark to an image. For PDFs use pdf_watermark. Returns the image with a text watermark (1-200 printable characters, DejaVu Sans Mono) at one of 9 positions, or tiled in a staggered grid, with opacity, font_size (default 5% of the short side), color, angle and margin; text larger than the image is shrunk to fit. Reads PNG, JPEG, WebP, GIF, TIFF, BMP, ICO and AVIF; other formats and images over 40 megapixels are refused (not charged). Output: base64 data_base64, without EXIF, GPS, XMP or IPTC; over 15 MB or 50 megapixels is a 413 (not charged). Images are not logged; a result is kept only with output "url" (24 h). Typically 0.5-2 s. Price: USD 0.002. Free: 3 imagepeek calls per IP per UTC day. Docs: https://tanod.dev/learn/image-watermark-api.html

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	No	Public http(s) URL of the image (at most 10 MB; private, internal and IP-literal hosts are refused); or use image_base64.
`text`	Yes	1-200 printable characters.
`tile`	No	A staggered grid (at most 2,500 marks).
`angle`	No	Text rotation in degrees, clockwise (-180 to 180, default 0).
`color`	No	Text colour as #rrggbb or #rrggbbaa (default #ffffff).	#ffffff
`format`	No	Output format (default: the input's; ICO in, PNG out).
`margin`	No	Pixels from the edge (default half the font size, at least 4); with tile, the gap between marks.
`output`	No	base64 (default): the file comes back inline as base64. url: the file is stored for 24 hours and the reply carries a download link (url, expires_at, bytes, content_type, sha256) instead of the base64, which keeps the file out of your context window.	base64
`opacity`	No	0 (invisible) to 1 (opaque); default 0.5.
`quality`	No	Encoder quality 1-100 (lossy formats).
`position`	No	Single mark's place: center, top, bottom, left, right, top-left, top-right, bottom-left or bottom-right (default).	bottom-right
`font_size`	No	Default: 5% of the short side.
`auto_orient`	No	Apply the EXIF orientation first.
`image_base64`	No	The image as standard or url-safe base64 (at most 10 MB decoded; a data:image/...;base64, prefix is fine); or use url.

Output Schema

TableJSON Schema

Name	Required	Description
`url`	No
`font`	No
`bytes`	No
`error`	No	Only on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object.
`input`	No
`marks`	No
`notes`	No
`width`	No
`format`	No
`height`	No
`sha256`	No
`source`	No
`final_url`	No
`font_size`	No
`operation`	No
`expires_at`	No
`source_url`	No
`data_base64`	No
`content_type`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Oct 15, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only mark it non-read-only, idempotent and non-destructive; the description goes far beyond that, disclosing accepted formats, refusal conditions (>40 MP or unsupported formats, not charged), metadata stripping (EXIF/GPS/XMP/IPTC), the 413 ceiling, retention (only stored with output=url, 24 h), privacy (not logged), latency, price and the free daily quota.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single dense paragraph, but front-loaded correctly: purpose, then routing, then capability detail, then limits/cost. Every clause carries operational value (formats, errors, pricing, retention), though the run-on semicolon structure is heavier than it needs to be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description need not explain return values, and it still states the base64/url contract and the 413 case. Annotations, 14 fully described parameters and the exhaustive limits/pricing coverage leave nothing an agent needs missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real detail the schema lacks: the DejaVu Sans Mono font face and the shrink-to-fit rule when text exceeds the image. The rest of the parameter recap (position, opacity, angle, margin, tile) largely restates what the schema already documents.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ("Add a text watermark to an image") and immediately distinguishes itself from the closest sibling by naming pdf_watermark for the PDF case. An agent can tell this apart from image_resize/image_convert/pdf_watermark without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"For PDFs use pdf_watermark" is an explicit when-to-use-else routing statement with the selecting condition, which is strong. It gives no guidance for the other plausible confusions in this large catalog (e.g., when to prefer image_strip_metadata or a resize/convert step), so it falls just short of the exhaustive when/when-not bar.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server