Skip to main content
Glama
Literature Evidence MCP

Literature Evidence MCP

by Furox-Art

pdf_page_provenance

User-supplied PDF: page hash, quote offsets, table and image bounding boxes.

Instructions

User-supplied PDF: page hash, quote offsets, table and image bounding boxes.

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": {
      "pdf_base64": "<pdf_base64>",
      "page_number": "<page_number>",
      "quote": "<quote>"
    },
    "name": "pdf_page_provenance"
  }
}

Input Schema

NameRequiredDescriptionDefault
quoteYes
pdf_base64Yes
page_numberYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.1

TDQS

D1.9/5.0
Behavior2/5

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

With zero annotations, the description carries the full burden and falls far short: it never states whether this is a pure read (implied by 'provenance' but not declared), what encoding or size limits apply to the binary payload, or what guarantees the returned offsets have. The enumeration of outputs is the only behavioral information offered.

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?

Eleven words with no waste, but this is under-specification rather than conciseness — the fragment is missing the verb that would make it a usable sentence. Length is not the problem; the absence of any actionable statement is.

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?

Required inputs include a base64 PDF blob, there are no annotations, no output schema, and 0% schema coverage, yet the description supplies nothing about the call contract. For a three-required-parameter tool handling an uploaded document, this is inadequate to invoke correctly.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate for three required parameters and it does not: pdf_base64 is never explained (encoding, full-document vs page, size limits), page_number's indexing base is unstated, and 'quote' is only obliquely gestured at via 'quote offsets' without saying it must be verbatim locating text.

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

Purpose2/5

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

The text is a noun-phrase fragment ('User-supplied PDF: page hash, quote offsets, table and image bounding boxes') that restates the tool name and lists apparent outputs rather than stating a verb+resource. An agent can infer it computes provenance for a PDF page, but the operation (extract? locate? return?) is never stated, and no sibling such as verify_source_quote or rust_locate_quote is distinguished.

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, when-not-to-use, or alternative guidance at all, despite several siblings (verify_source_quote, rust_locate_quote, verify_evidence_ledger) that plausibly overlap. The only contextual hint is 'User-supplied PDF', which weakly signals it applies to user-uploaded files rather than retrieved ones.

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