POSTECH PLMS MCP

plms_read_attachment

Read-onlyIdempotent

Extract text and page, slide, or cell locators from PDF, Office, HWP, HTML, or ZIP attachments by URL. Paginate with offset/limit and select a ZIP member to read without extracting it.

Instructions

Read PDF, DOCX, PPTX, XLSX, HWP/HWPX, HTML/text attachment linked on source_url. ZIP lists members; set archive_member to read one without executing it. Return source locators and next_offset. No OCR.

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": {
      "source_url": "<source_url>",
      "attachment_url": "<attachment_url>"
    },
    "name": "plms_read_attachment"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No
`offset`	No
`source_url`	Yes
`archive_member`	No
`attachment_url`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 20, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the description adds genuinely new context: 'No OCR' discloses a capability limit, and 'without executing it' reassures about archive handling. It also names the return payload ('source locators and next_offset'). This is solid value beyond the annotations.

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

Conciseness5/5

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

Four tight sentences, front-loaded with the formats and core action, then the archive edge case, then the return note and the OCR caveat. Every sentence adds distinct information with no padding.

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

Completeness4/5

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

An output schema exists, so return values need not be spelled out, and annotations cover safety. The main gap is pagination semantics (limit/offset) and the meaning of the two URL parameters, which an agent would need to call it correctly.

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 0%, so the description carries the full burden. It clarifies archive_member's role and ties source_url to the attachment link, and 'next_offset' hints at pagination, but limit, offset, and attachment_url are left entirely undefined. Partial compensation only.

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

Purpose5/5

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

States a specific verb (read) and resource (attachment) plus the exact supported formats (PDF, DOCX, PPTX, XLSX, HWP/HWPX, HTML/text), which clearly distinguishes it from plms_read_page in the sibling list. An agent can tell this handles file attachments rather than HTML pages without opening the schema.

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

Usage Guidelines3/5

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

Provides conditional guidance for the archive case ('ZIP lists members; set archive_member to read one without executing it') and a clear limitation ('No OCR'), but never states when to choose this over plms_read_page or what source_url vs attachment_url mean in practice. Usage is implied rather than explicitly routed against alternatives.

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