Skip to main content
Glama

pdf_watermark

Applies a text watermark to a PDF with configurable text, angle, color, opacity, and font size for labeling or copyright marking.

Instructions

Applies a text watermark to a PDF. [Input: PDF (.pdf) | Output: PDF (.pdf)]

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "input": "<input>",
      "text": "<text>",
      "output": "<output>"
    },
    "name": "pdf_watermark"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe watermark text to apply.
angleNoAngle of the watermark (default 45).
colorNoColor of the watermark (e.g. 'gray', 'red').
inputYesThe input PDF file path.
outputYesThe output PDF file path.
opacityNoOpacity of the watermark (0 to 1, default 0.2).
font_sizeNoFont size.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations supplied, the description carries the full disclosure burden and mostly does not meet it. It does convey the input/output contract (PDF in, PDF out) and, via the required output path, implies a non-destructive write to a new file rather than in-place modification. It says nothing about permission requirements, encrypted or malformed input handling, whether existing watermarks are preserved, or how the watermark is positioned or tiled across pages.

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?

Two compact elements: the purpose sentence, which is front-loaded, followed by a terse I/O signature. Nothing is padded or redundant. The bracketed I/O notation is boilerplate but it delivers the format contract cheaply.

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

Completeness3/5

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

A seven-parameter mutation tool with no annotations and no output schema needs at least some behavioral grounding, and the description supplies only the format contract. Because the schema is fully self-documenting on parameters, the practical gap is the behavioral side: rendering behavior across pages and error conditions on bad input remain unexplained.

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

Parameters3/5

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

Schema description coverage is 100% and every one of the seven parameters, including defaults for angle (45) and opacity (0.2), is documented in the schema. The description adds no extra meaning such as units, allowed color names, or how angle is measured, so the baseline of 3 applies.

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

Purpose4/5

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

States a specific verb and resource: 'Applies a text watermark to a PDF.' An agent can distinguish this from conversion siblings like html_to_pdf or md_to_pdf. It does not explicitly contrast with the closer sibling pdf_annotate, which also writes visible marks onto a page, so the differentiation is not complete.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no statement of when to prefer this over pdf_annotate or pdf_bates, and no prerequisites such as whether the source PDF must be unencrypted. The agent must infer all routing decisions from the name alone.

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