Skip to main content
Glama

export

Saves a mind map or flowchart diagram to a local file in SVG, PNG, JSON, or Markdown so you can share, archive, or reuse it.

Instructions

The view writes the diagram to a file on this machine.

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": {
      "docId": "<docId>",
      "format": "<format>"
    },
    "name": "export"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNoSVG text or a PNG data URL, drawn by the view
docIdYesThe docId a visualize result gave you
formatYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.4/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the safety profile is partly covered, yet the description adds little beyond "a file on this machine." Critically, it never says where on disk the file lands, whether an existing file is overwritten, or how the resulting path is communicated — and there is no output schema to answer that last question.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short sentence with no wasted words, which is good, but the brevity is under-specification rather than economy. The passive framing ("The view writes") buries the subject and the destination detail the agent actually needs.

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

Completeness2/5

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

For a write tool with no output schema, the description should at minimum convey where the file is written and how the caller learns of it; neither appears. Combined with three parameters and only partial schema coverage, the definition leaves real gaps an agent cannot resolve from structured fields.

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 coverage is 67%: docId and data are described in the schema, while format is documented only by its enum values (svg/png/json/md). The description adds no meaning to any parameter — not that data is the rendered SVG/PNG payload, not what the format choices imply about output. It does not compensate for the uncovered parameter.

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

Purpose3/5

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

"Writes the diagram to a file on this machine" gives a verb and a destination, so an agent can tell this is a filesystem output operation rather than a state or DB write. But the sentence is framed as "the view writes," which obscures whether the caller or the view performs the action, and it never clarifies how export differs from save_state or visualize.

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?

There is no when-to-use guidance at all: no statement of when to export versus save_state or visualize, no prerequisite that a visualize result must exist first, and no exclusions. The agent must infer from the sibling names alone.

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