Lossless PDF optimization: garbage collection, stream re-compression. No quality loss. Good for PDFs with redundant data; effect is small on already-optimized files. Free anonymous tier: 20 calls/day per IP, files up to 10MB. Larger files / more calls need an API key (https://ko-fi.com/yugutou/shop) or the free website https://pdfslim.app.
| Name | Required | Description | Default |
|---|---|---|---|
| file_base64 | Yes | The PDF file contents, base64-encoded. |
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?
With no annotations, the description carries the burden. It discloses lossless behavior, rate limits (20 calls/day/IP), file size cap (10MB), and auth requirements (API key for larger limits). Missing return value details, but substantial behavioral transparency.
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 compact and front-loaded: purpose first, then usage guidance, then limitations/auth. Every sentence adds value without redundancy.
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 simple one-parameter tool with no output schema or annotations, the description provides sufficient context on purpose, usage, and constraints. It lacks explicit return value description, but the expected output (optimized PDF) is implicit and reasonably inferable.
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 covers the single parameter (file_base64) at 100%, and the description adds meaningful constraints: file size limit and API key requirement for larger files, which helps agents validate inputs before calling.
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 it performs lossless PDF optimization with specific techniques (garbage collection, stream re-compression) and explicitly notes no quality loss. This distinguishes it from likely lossy compression tools.
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?
Provides clear usage context: good for PDFs with redundant data, and notes effect is small on already-optimized files. However, it does not explicitly compare with sibling tools like compress_pdf or state when not to use it.
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.
compress_pdf and optimize_pdf both reduce file size, which creates some overlap, but the descriptions clearly distinguish lossy re-encoding from lossless optimization. inspect_pdf is entirely separate.
All tool names follow a consistent verb_noun pattern: compress_pdf, inspect_pdf, optimize_pdf. This is uniform and predictable.
With only three tools, the set is tightly scoped to the server's stated purpose of PDF compression and optimization. Every tool serves a clear function without unnecessary bloat.
The server covers the core operations for PDF size management: inspect to assess the file, compress for lossy size reduction, and optimize for lossless cleanup. No obvious gaps for its intended use case.
