Split a PDF into semantic chunks ready for embeddings (RAG). Each chunk carries its text, estimated tokens, starting page, section heading and the source element ids for citation.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | http(s) URL of the PDF to chunk. | |
| maxTokens | No | Target chunk size in tokens. Default 512. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / maxTokens / descriptionPrevious value: -"Tamaño objetivo de chunk en tokens. Por defecto 512."New value: +"Target chunk size in tokens. Default 512."Input schema / properties / url / descriptionPrevious value: -"URL http(s) del PDF a trocear."New value: +"http(s) URL of the PDF to chunk."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully describes what the output contains (text, tokens, page, heading, element IDs). However, it does not mention required permissions, destructive effects, or operational constraints (e.g., file size limits).
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?
Two sentences, no wasted words, front-loaded with the core action (split PDF into chunks) followed by output details.
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?
The output schema is absent, but the description compensates by detailing chunk contents. Lacks error conditions, limits, or prerequisites. For a simple two-parameter tool, it is largely complete.
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% (both url and maxTokens have descriptions). The tool description adds context about output but no additional meaning to the parameters beyond 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 uses specific verb 'Split' and resource 'PDF into semantic chunks'. It explicitly states the RAG/embeddings use case and distinguishes from siblings like extract_pdf (raw text) and list_tables (tables).
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 usage for RAG embeddings but does not provide explicit when-to-use, when-not-to-use, or alternatives. No comparison with sibling tools like extract_pdf.
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.
Each tool targets a distinct operation: PDF extraction, table extraction, chunking, link creation, listing, stats, and revocation. No overlapping purposes.
All tools follow a consistent verb_noun pattern with lowercase and underscores, e.g., create_doc_link, extract_pdf, list_tables.
Seven tools is an appropriate scope for a PDF extraction and link management server, covering both processing and lifecycle operations without excess.
Covers core extraction (text, tables, chunks) and link management (create, list, stats, revoke). Minor gap: no update operation for doc links, but not critical.