Skip to main content
Glama
Sign In

CalderFlow

by com.calderflow
OverviewDiscussionsAdmin

edit_chart

Edit an existing chart. Call get_chart first to see its current spec, then pass tool_calls (surgical edits) and/or mermaid (full source replacement, flowchart/ERD only). A create_* tool call replaces the chart's data wholesale and can switch its type. Valid tool names — flowchart: style_chart, update_node, delete_node, add_node, connect_nodes, delete_edge, organize_sections, add_section, update_section, delete_section, move_node_to_section, set_node_icon ({nodeId, icon} or icon "none" to remove), set_key_step ({nodeId} or "none"); process/funnel/timeline/lifecycle: set_item_icon ({itemId, icon} or icon "none") and set_key_item ({itemId} or "none"), plus icon on add_* calls; any type: set_slide_text ({headline, takeaway}) for the Designed presentation slide and set_walkthrough ({steps:[{id, caption}]}) for the Walkthrough (a flowchart with 2+ sections walks one step per section, using subgraph IDs; otherwise use node or item IDs); chevron: create_chevron_chart, add_step, update_step, delete_step, reorder_steps, set_presentation_steps, style_chevron_chart; funnel: create_funnel_chart, add_funnel_stage, update_funnel_stage, delete_funnel_stage, reorder_funnel_stages, style_funnel_chart; lifecycle: create_lifecycle_chart, add_lifecycle_milestone, update_lifecycle_milestone, delete_lifecycle_milestone, update_lifecycle_phase, style_lifecycle_chart; timeline: create_timeline_chart, add_timeline_event, update_timeline_event, delete_timeline_event, reorder_timeline_events, style_timeline_chart; erd: create_erd_chart, add_erd_entity, update_erd_entity, delete_erd_entity, add_erd_attribute, update_erd_attribute, delete_erd_attribute, add_erd_relationship, update_erd_relationship, delete_erd_relationship, set_erd_direction, style_erd_chart (set_erd_direction takes {direction: "vertical"|"horizontal"}). For chevron Presentation-only selection/order edits, use set_presentation_steps with {stepIds:[up to 6 existing IDs in featured order]} (or null to reset to all); never reorder_steps, delete_step, or rename Full steps to change a Presentation summary. Use organize_sections with {sections:[{sectionId,title,nodeIds}], ungroupedNodeIds?} for a complete multi-section regroup; omitted nodes are placed with their closest connected section. Input shapes otherwise match the get_chart spec data (e.g. add_node takes {nodeId, label, shape?, connectFrom?, connectTo?}; style_chart takes {target: ''|'all', bgColor?, textColor?, borderColor?}).

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": {
      "chart_id": "<chart_id>"
    },
    "name": "edit_chart"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNoNew title (optional).
mermaidNoFull replacement mermaid source (flowchart/ERD charts only).
chart_idYesChart id from create_* / list_charts.
tool_callsNoOrdered edit operations: [{tool, input}].

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and does well: it discloses that create_* calls replace chart data wholesale and can change chart type, and that mermaid performs full source replacement for certain chart types. It also warns against certain destructive Presentation edits. It does not cover permissions, reversibility, or error behavior, so it falls short of fully transparent.

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?

The description is front-loaded and purposeful, beginning with the core action and workflow before detailed tool lists. It is very dense and long, but the complexity of the nested tool_calls interface justifies most of the detail. Greater structural separation would improve readability.

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?

For a complex mutation tool with no output schema, the description is largely complete: it covers invocation workflow, valid nested operations, input examples, and key constraints. Remaining gaps include return values and failure behavior, which are not described.

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

Parameters5/5

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

Schema coverage is 100%, but the description adds substantial meaning beyond the schema's generic tool_calls array. It enumerates valid tool names by chart type, explains nested input shapes with examples, documents mermaid restrictions, and clarifies presentation-step and section-regroup semantics.

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?

The first sentence states a specific verb and resource: "Edit an existing chart." It clearly distinguishes editing from creation by noting that create_* calls replace data wholesale and can switch chart type.

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

Usage Guidelines5/5

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

The description gives explicit workflow guidance: call get_chart first, use tool_calls for surgical edits, and use mermaid only for full replacement of flowchart/ERD charts. It also specifies chart-type-specific alternatives and constraints, such as using set_presentation_steps rather than reorder_steps for Presentation-only ordering.

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

All CalderFlow toolsInspect
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