Kaiku

Copy pdf to wiki

copy_pdf_to_wiki

Destructive

Copy a PDF from another site onto a wiki page by its link — an article a conspectus cites, kept here in case it disappears there. The server fetches it: an https address on the public internet only, a PDF by its bytes, at most 50 MB. The copy is attached to the page (pageId, or spaceKey + title) under 'filename' or the address's own name, with where it came from and when; the page's history says who copied it. It is the project's working copy: shown to the project's members, and to a reader from outside a public project only as the link to the original. Once attached, pdf_page_image shows its pages, search finds its words, and «Recognize with formulas» (recognize_pdf) can read it with its formulas. Requires permission to edit the page.

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": {
      "url": "<url>"
    },
    "name": "copy_pdf_to_wiki"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	The PDF's address, https.
`title`	No	Exact page title, when identifying the page by title.
`pageId`	No	Page id (as returned by search_wiki).
`filename`	No	The name to keep it under, e.g. 'toda-2003.pdf'. The address's own name otherwise.
`spaceKey`	No	Space key, when identifying the page by title.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 7, 2026

TDQS

A4.1/5.0

Behavior3/5

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

Adds substantial context beyond the annotations: server-side fetch, https-only public internet address, must be a PDF by its bytes, 50 MB cap, provenance metadata recorded, visibility rules (project members see it; outside readers of a public project get only the original link), and the edit-permission requirement. However, annotations declare destructiveHint=true and the description never explains what is destructive — e.g. whether an existing attachment with the same 'filename' is overwritten. That is the one behavioral trait an agent most needs here.

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

Conciseness4/5

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

Front-loaded with the action and motive, then constraints, then effects, then permission — a sensible order with no filler sentences. It is dense to the point of being a single long paragraph, and the visibility sentence is more detailed than an agent needs to invoke the tool.

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?

For a 5-parameter mutation with no output schema, it covers source constraints, page/filename resolution, resulting provenance, visibility, downstream tooling, and the permission requirement. The remaining gap is failure behavior — what happens on a duplicate filename, an oversized file, or a non-PDF response.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds the disambiguation rule the schema leaves implicit: the page is identified either by pageId or by spaceKey + title, and the filename falls back to the address's own name. That is real added meaning, though the url constraint (https, public, PDF bytes, ≤50 MB) is partially restated rather than expanded.

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 and resource — copy a PDF from another site onto a wiki page by its link — and adds the mechanism (the server fetches it) and the motive (an article a conspectus cites, kept here in case it disappears there). That framing separates it from add_wiki_attachment/add_attachment, which handle uploads rather than server-side fetches.

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

Usage Guidelines4/5

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

Gives a clear situation for use (preserving a cited external article) and implies the alternative path by emphasizing 'from another site ... by its link'. It also points forward to follow-on tools (pdf_page_image, search, recognize_pdf) so the agent knows what this enables. It never states an explicit exclusion, e.g. what to do when the file is already local.

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

All Kaiku tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?