mcptask.online

CreateAttachmentLinkTool

Returns a link the user opens to attach files (screenshots, photos, PDFs) to a piece themselves, without signing in. Use this when the user wants a file attached that you only see in the chat (a pasted screenshot or photo): you cannot upload it yourself. Give the user the returned link; they open it and pick the file. The link works for 30 minutes, only for this piece.

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": {
      "account_code": "<account_code>",
      "piece_relative_id": "<piece_relative_id>"
    },
    "name": "CreateAttachmentLinkTool"
  }
}

Input Schema

Name	Required	Description	Default
`account_code`	Yes	Account code (e.g., "bcp", "jchsoft")
`piece_relative_id`	Yes	Relative ID of the piece the files will be attached to

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations only say non-read-only and non-destructive; the description adds real behavior the agent needs: no sign-in required, link expires in 30 minutes, and the link is scoped to this one piece. It does not say whether the link is single-use or accepts multiple files, and the 'opens without signing in' framing sits slightly oddly against openWorldHint=false, though it is not a direct contradiction.

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 short sentences, front-loaded with what is returned, then the trigger condition, then the required follow-up action, then the expiry constraint. Every sentence carries distinct information with no repetition.

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

Completeness5/5

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

There is no output schema, but the description covers the return value ('Returns a link', 'Give the user the returned link'), the agent's follow-up obligation, and the lifetime/scope constraints. For a two-parameter tool with full schema coverage, nothing needed to call it correctly is missing.

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 coverage is 100%, so both account_code and piece_relative_id are already documented. The description reinforces that the link targets a specific piece but adds no format, validation, or edge-case meaning beyond the schema, so the baseline of 3 applies.

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 opens with a specific verb and resource: it returns a link that lets the user attach files to a piece. It clearly separates itself from a direct-upload path by stating 'you cannot upload it yourself,' which implicitly rules out AddAttachmentTool, but it never names that sibling or CreateUploadUrlTool, so an agent must infer the boundary.

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 a concrete trigger ('when the user wants a file attached that you only see in the chat (a pasted screenshot or photo)') and states why the agent must delegate rather than act directly. What is missing is an explicit when-not clause naming the alternative tool to use when the agent does hold the file bytes.

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

All mcptask.online 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?