Skip to main content
Glama

get_artifact

Fetch a manifest-listed simulation artifact by run ID and artifact ID, returning UTF-8 text or base64-encoded PNG/GIF/NPZ with SHA-256 verification (up to 2 MiB).

Instructions

Transfer a manifest-listed text artifact (UTF-8) or PNG/GIF/NPZ (base64), including verified SHA-256, up to 2 MiB.

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": {
      "run_id": "<run_id>",
      "artifact_id": "<artifact_id>"
    },
    "name": "get_artifact"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idYes
artifact_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.7.1

TDQS

B3.2/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and does well: it discloses the per-type encoding contract (UTF-8 for text, base64 for PNG/GIF/NPZ), that SHA-256 integrity is verified, and a hard 2 MiB limit. It stops short of stating read-only safety, permission requirements, or the error behavior when an artifact is missing or exceeds 2 MiB.

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?

One dense sentence with the resource type and constraints front-loaded and no filler. It is well-packed, though the parenthetical encoding clauses make it read like a spec fragment rather than a framed instruction.

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?

An output schema exists, so return structure need not be described, and content formats, integrity, and size are covered. However, the description says nothing about how the caller should locate a valid artifact_id or what the tool does when the manifest entry is absent, which is a meaningful gap for a two-required-parameter fetch.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate for both parameters, and it does not. Neither run_id nor artifact_id is explained; the phrase 'manifest-listed' hints that artifact_id is drawn from a manifest, but the relationship between run_id and artifact_id is left entirely to inference.

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 concrete verb and resource ('Transfer a manifest-listed text artifact'), and goes further by enumerating supported content types and encodings plus a size ceiling. It does not differentiate itself from the closest sibling (get_render_artifact), and 'Transfer' is an unusual choice of verb for a get-style tool, but the operation is unmistakable.

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

Usage Guidelines2/5

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

The only usage signal is the implicit precondition that the artifact must be manifest-listed. There is no statement of when to pick this over get_render_artifact or get_result, no mention of what happens for artifacts not in the manifest, and no guidance on expected failure modes.

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