Skip to main content
Glama
orchestra-hq

Orchestra MCP Server

Official
by orchestra-hq
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Download Task Run Artifact

download_task_run_artifact
Read-only

Download a task run artifact file as base64-encoded content. For files larger than 3MiB, fetch in chunks using a range header.

Instructions

Download a task run artifact file, returned base64-encoded. Artifacts such as a dbt manifest.json are often tens of MB. At most 3MiB of file content is returned per call; fetch larger files in chunks by passing range_header (e.g. 'bytes=0-3145727') and advancing the range each call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filenameYes
account_idNoAct on this account rather than the one the credential resolves to. Omit it to use the credential's own account. An API key is issued to a single account, so it may only name that account; an OAuth token may name any account its grant covers.
task_run_idYes
range_headerNo
pipeline_run_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.1
    • addedInput schema / properties / account_id
      Added value: +{
+  "anyOf": [
+    {
+      "format": "uuid4",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Act on this account rather than the one the credential resolves to. Omit it to use the credential's own account. An API key is issued to a single account, so it may only name that account; an OAuth token may name any account its grant covers."
+}
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only supply readOnlyHint=true; the description adds the genuinely non-obvious operational facts: the response is base64-encoded, capped at 3MiB per call, and larger files must be paginated with advancing byte ranges. That is exactly the kind of behavior an agent would otherwise get wrong.

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 tight sentences, front-loaded with purpose then the size constraint and the chunking recipe. No filler and nothing buried.

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?

With no output schema, the description correctly supplies the return format and size limit, which is what an agent needs to consume the result. Missing is any hint that filenames come from list_task_run_artifacts and any statement of behavior once the range exceeds the file length.

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 only 20% (account_id is the sole documented param), so the description has to carry weight: it explains range_header's format and gives a concrete example. The three required identifiers (pipeline_run_id, task_run_id, filename) get no explanation, though their names are largely self-describing, so this partially compensates rather than fully.

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 (Download) and resource (task run artifact file) and adds the return encoding (base64), which cleanly separates it from the sibling download_task_run_log without the agent needing to open a schema.

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 clear conditional guidance for range_header: use chunks when the file exceeds 3MiB, with a concrete example range value. It does not, however, point at list_task_run_artifacts as the way to discover valid filenames, so the entry path is left to inference.

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

Deploy Server

Other Tools