Org charts from a team list
Scored across 1 tool
Only one tool exists, so there is no possibility of misselection between tools. The description also explicitly scopes out adjacent requests (family trees, flowcharts, seating charts), further reducing confusion.
A single, clear verb_noun name (make_org_chart) in snake_case that directly reflects the action and resource. No competing conventions to clash with.
One tool is thin for what is effectively a chart-generation workflow; options like re-styling, editing, or reformatting an existing chart have nowhere to go. The single tool is rich in parameters, which partly compensates, but the surface feels minimal.
The tool covers input (list or CSV/XLSX), layout, styling, and multiple output formats (SVG, PDF sizes), which is solid for a one-shot generation. However, there is no way to retrieve, modify, or re-export a previously generated chart, leaving dead ends for iterative workflows.
Use this when the user wants an org chart maker, an organizational chart maker, or to create an org chart, a company hierarchy chart or a team structure chart from a reporting list. Give the people (2-500, with who each reports to) or attach a CSV/XLSX file, and it lays out a tidy tree with no overlapping boxes, colours boxes by department or level, and returns downloadable vector SVG and fitted landscape PDF files (Letter, A4, A3 or Tabloid). Limits: name and title cards only (no photos), up to 500 people, automatic layout (no manual dragging); PDF fonts support Latin, Greek and Cyrillic, and unsupported scripts or emoji produce an input error. Do not use for family trees, flowcharts or seating charts.
| Name | Required | Description | Default |
|---|---|---|---|
| file | No | Optional CSV or XLSX file with a header row and one person per row, columns id/name/title/manager/department (matched case-insensitively), e.g. team.csv or org.xlsx. | |
| paper | No | Landscape PDF page size: letter (default), a4, a3 or tabloid (11x17 in), e.g. a4. | |
| people | No | The people and who they report to, 2-500 records, e.g. [{"name":"Ada Lee","title":"CEO"},{"name":"Ben Cole","manager":"Ada Lee"}]. Give this or attach a file. | |
| color_by | No | Box colour: department uses one colour per department (default), level shades boxes by depth, none leaves them white, e.g. level. | |
| orientation | No | Chart direction: top_down puts each manager above their reports (default), left_right puts the manager to the left, e.g. left_right. |
| Name | Required | Description |
|---|---|---|
| tops | Yes | |
| paper | Yes | |
| levels | Yes | |
| people | Yes | |
| source | Yes | |
| preview | Yes | |
| color_by | Yes | |
| warnings | Yes | |
| downloads | Yes | |
| unassigned | Yes | |
| departments | Yes | |
| orientation | Yes | |
| download_note | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (which already declare readOnly, idempotent, non-destructive, closed-world), the description discloses real operational traits: card-only rendering with no photos, automatic layout with no manual dragging, a hard 500-person cap, and the fact that unsupported scripts or emoji produce an input error rather than a degraded output. That font/error constraint in particular is the kind of failure mode an agent cannot get from the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the trigger condition and dense throughout; the limits-and-exclusions sentences each carry distinct information. It is a single run-on paragraph, though, and the input/output mechanics, styling options, limits and exclusions would be easier to scan as separate lines.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 5-parameter, no-required-parameter generative tool with nested people records, the description covers input forms (inline list or file), the full option surface (paper sizes, color_by, orientation), output artifacts, and hard limits. An output schema exists, so it correctly does not re-explain return values.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3; the description still adds value by stating the 2-500 people range, that manager references resolve by id or name, that department drives the color_by choice, and that CSV columns are matched case-insensitively. It does not, however, reconcile the stated 500-person ceiling with the schema's maxItems of 1000, leaving the true cap ambiguous.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('create an org chart') and enumerates the user-phrasings it covers (org chart maker, company hierarchy chart, team structure chart), plus what input it consumes (a reporting list or CSV/XLSX) and what it produces (SVG and PDF). No sibling tools exist, so no differentiation is needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Opens with an explicit trigger ('Use this when the user wants...') and closes with explicit exclusions ('Do not use for family trees, flowcharts or seating charts'). Both halves of the routing decision are stated outright, leaving nothing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
make_org_chartTurn a description of your team into an editable org chart. Free, no signup.
Create native, editable SmartArt diagrams for Microsoft Word and PowerPoint.
Visual AI for strategic thinking — SWOT, flowcharts, mindmaps, Gantt diagrams as polished SVG.
Create scheduled Gantt charts with critical path from a plain-language plan — no account or key.
Add one secure layer between your agents and this server.
