Skip to main content
Glama
andr3medeiros

PDF Manipulation MCP Server

pdf_add_annotation

Add annotations like text, comments, or highlights to PDF documents by specifying page, position, and content for document collaboration and markup.

Instructions

Add an annotation to a PDF.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pdf_pathYes
page_numberYes
annotation_typeYes
xYes
yYes
widthYes
heightYes
contentYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The primary handler function for the 'pdf_add_annotation' tool, decorated with @mcp.tool() for automatic registration in FastMCP. It adds text, highlight, underline, or strikeout annotations to a PDF page at specified coordinates using PyMuPDF.
    @mcp.tool()
    async def pdf_add_annotation(
        pdf_path: str,
        page_number: int,
        annotation_type: str,
        x: float,
        y: float,
        width: float,
        height: float,
        content: str
    ) -> str:
        """Add an annotation to a PDF."""
        if not os.path.exists(pdf_path):
            return f"Error: PDF file not found: {pdf_path}"
        
        if not validate_pdf_file(pdf_path):
            return f"Error: Invalid PDF file: {pdf_path}"
        
        try:
            # Open PDF document
            doc = fitz.open(pdf_path)
            
            # Validate page number
            if not validate_page_number(doc, page_number):
                doc.close()
                return f"Error: Invalid page number {page_number}. Document has {len(doc)} pages."
            
            # Get the page
            page = doc[page_number]
            
            # Create rectangle for annotation
            rect = fitz.Rect(x, y, x + width, y + height)
            
            # Add annotation based on type
            if annotation_type == "text":
                annot = page.add_text_annot(rect, content)
            elif annotation_type == "highlight":
                annot = page.add_highlight_annot(rect)
                annot.set_info(content=content)
            elif annotation_type == "underline":
                annot = page.add_underline_annot(rect)
                annot.set_info(content=content)
            elif annotation_type == "strikeout":
                annot = page.add_strikeout_annot(rect)
                annot.set_info(content=content)
            else:
                doc.close()
                return f"Error: Invalid annotation type: {annotation_type}"
            
            # Update annotation appearance
            annot.update()
            
            # Generate output filename
            output_path = generate_output_filename(pdf_path)
            
            # Save the modified PDF
            doc.save(output_path)
            doc.close()
            
            return f"Successfully added {annotation_type} annotation to PDF. Output saved to: {output_path}"
            
        except Exception as e:
            return f"Error adding annotation to PDF: {str(e)}"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.0
    • addedInput schema / title
      Added value: +"pdf_add_annotationArguments"
  2. First observed

TDQS

C2.3/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Add' implies mutation, but it does not state whether the file is modified in place, what annotation types are supported, or any required permissions. This is a significant gap for a tool that likely modifies the PDF.

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

Conciseness2/5

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

The description is a single short sentence, which is concise, but it is under-specified for a tool with 8 required parameters and no additional documentation. It does not front-load important usage details and lacks structure that would help an agent parse relevant information quickly.

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

Completeness1/5

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

Given the tool's complexity (8 parameters, no annotation coverage, no schema descriptions), the description is completely inadequate. It does not explain annotation types, coordinate systems, page indexing, or the output format, making it impossible for an agent to invoke the tool correctly without external knowledge.

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

Parameters1/5

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

Schema description coverage is 0% and the description adds no information about any of the 8 parameters. The parameters (x, y, width, height, annotation_type, etc.) are entirely unexplained, leaving the agent to guess their meanings and formatting.

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?

The description clearly states the tool's action ('Add an annotation') and the target resource ('a PDF'), using a specific verb. It does not explicitly differentiate from sibling tools like pdf_add_text or pdf_add_image, but 'annotation' is a distinct concept in PDF terminology, providing some differentiation.

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?

No guidance is provided on when to use this tool versus alternatives. The description does not mention exclusions, prerequisites, or typical scenarios, leaving the agent without context for appropriate selection.

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