SKEIN

skein_attachments

Destructive

Files attached to an issue or to one of its comments. Uploading takes two calls — action="upload_url", then action="confirm" once the file has landed in storage; an unconfirmed attachment is invisible to list. Presigned URLs expire after 10 minutes. Read-only actions: list, metadata, get_url.

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": {
      "action": "<action>"
    },
    "name": "skein_attachments"
  }
}

Input Schema

Name	Required	Description
`action`	Yes	What to do: - "upload_url" → mint a presigned upload URL and create a pending attachment row. The size limit is per instance and is returned as `maxSizeBytes` (over it: attachment_too_large); executable files are refused by extension (attachment_mime_blocked). - "confirm" → mark an uploaded file ready (idempotent; re-emits no event on a second call). - "list" → list every confirmed attachment on an issue. - "metadata" → filename, contentType, sizeBytes, status and uploader of one attachment. - "get_url" → mint a presigned download URL for a ready attachment. - "delete" → hard-delete the row and remove the stored object.
`issueId`	No	Full hierarchical issue id (e.g. "demo-42"). Required for upload_url and list.
`filename`	No	Original filename, kept as Content-Disposition on download. Required for upload_url.
`commentId`	No	Optional UUID of a comment under the issue. When set on upload_url, the attachment is scoped to that comment instead of the issue itself.
`sizeBytes`	No	Exact file size in bytes. The presigned policy binds this value — uploads of a different size are rejected by S3. Required for upload_url.
`contentType`	No	MIME type of the upload (e.g. "image/png"). Re-checked at confirm time. Required for upload_url.
`attachmentId`	No	Attachment UUID, as returned by upload_url or list. Required for confirm, metadata, get_url and delete.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description doesn't need to re-establish safety, and it adds genuinely new behavior: the two-phase commit model, the invisibility of unconfirmed attachments, and the 10-minute URL expiry. It does not cover permission or auth requirements, and the hard-delete consequence for the destructive action lives only in the schema enum text.

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?

Three short sentences with zero filler: resource first, then the stateful upload workflow with its consequence, then the expiry constraint and the read-only action set. Every sentence carries information an agent needs before constructing a call.

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 six-action tool with no output schema and fully documented parameters, the description adequately orients the caller around the nontrivial part (the two-step upload) and the safe read actions. It omits scoping details such as commentId redirecting the attachment away from the issue, and says nothing about what list returns, but those gaps are largely covered by the schema.

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 100%, and the schema already documents each action, required fields per action, and error codes like attachment_too_large and attachment_mime_blocked. The description adds only workflow-level meaning (the upload/confirm pairing) rather than parameter-level detail, which is the expected baseline when the schema does the heavy lifting.

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

Purpose4/5

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

The description states the resource precisely ("Files attached to an issue or to one of its comments") and then clarifies the action surface by naming the two-call upload flow and the read-only actions. It is clear what the tool manages, though it never names a single verb and doesn't differentiate itself from related sibling tools like skein_comment, which is left implicit.

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?

It gives concrete operational guidance: uploading requires action="upload_url" followed by action="confirm", and an unconfirmed attachment is invisible to list. It also warns that presigned URLs expire after 10 minutes, which changes how a caller should sequence work. It stops short of explicit when-not-to-use or pointing at an alternative tool, so it is strong context without full routing.

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

All SKEIN tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.