Skip to main content
Glama

Attach a file to a task or a document

attach

Copy a local file into Tisty to keep it with a task's journal or append it to a document as a picture or card. Use it only for files you were asked to attach.

Instructions

Copy a file from this machine into Tisty: with task onto its journal, with doc at the end of that document as a picture or a card. Up to 650 MB; an HTML page is kept, never run. Attach only what you were asked to.

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": {
      "path": "<path>"
    },
    "name": "attach"
  }
}

Input Schema

NameRequiredDescriptionDefault
docNoThe document's id, to add it there
pathYesA file under Downloads, Documents, Pictures, Desktop or the temporary folder
taskNoThe task id, to keep it with a task
labelNoWhat to call it; defaults to the file's name

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.47.0
    • changedInput schema / properties / path / description
      Previous value: -"A path to a file on this machine"New value: +"A file under Downloads, Documents, Pictures, Desktop or the temporary folder"
  2. Changed3 schema fields changedv1.43.2
    • changedInput schema / properties / doc / description
      Previous value: -"The document's id, if it goes in a document — an opaque name like `q7ntmzbm-0001`, which `docs` lists"New value: +"The document's id, to add it there"
    • changedInput schema / properties / label / description
      Previous value: -"What to call it. Defaults to the file's own name"New value: +"What to call it; defaults to the file's name"
    • changedInput schema / properties / task / description
      Previous value: -"The task id, if it is kept with a task"New value: +"The task id, to keep it with a task"
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Adds real behavioral context beyond the annotations: a 650 MB size ceiling, the fact that HTML uploads are stored and never executed (a meaningful safety disclosure), and the rendered outcome for documents (picture or card). It does not address what happens on re-attaching the same file, which is notable given idempotentHint=false, but the added detail is substantial.

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?

Two tight sentences with the core action front-loaded, then the destination branches, then the limits and caution. Every clause carries information: size cap, HTML handling, and scope restriction are all load-bearing.

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

Completeness3/5

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

For a mutation tool with full schema coverage, annotations, and no output schema, most of what an agent needs is present. The notable gap is precedence when both `task` and `doc` are provided, plus any hint about the returned value or duplicate handling, which matters since the operation is neither idempotent nor read-only.

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 earns more by explaining the consequence of each destination parameter rather than restating their types: `task` lands on that task's journal, `doc` appends as a picture or a card. `path` and `label` add little beyond their schema text, but the destination semantics are genuinely enriched.

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?

States a specific verb and resource ("Copy a file from this machine into Tisty") and then differentiates two destination modes: `task` puts it on the task's journal, `doc` puts it at the end of a document as a picture or card. The purpose is unambiguous, but no sibling is named or contrasted (e.g. file_doc, import_doc), so the agent must infer which tool owns which attachment workflow.

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?

The description implicitly guides parameter choice by pairing `task` with journals and `doc` with document placement, and adds the guardrail "Attach only what you were asked to." However, there is no explicit when-to-use versus alternatives, no statement about prerequisites, and no guidance on what to do when both `task` and `doc` are supplied.

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