Skip to main content
Glama

export_diagram

Read-only

Exports the current project to a standard, portable text format (anti-lock-in: the diagram goes to GitHub, GitLab, Notion, a Mermaid editor, a doc...). org / entity / data-source / arch / process / journey → Mermaid (.mmd, rendered natively by GitHub/Notion). captable → Markdown (.md: holders table with %, funding rounds table, + a Mermaid pie chart of the shares). The 'kind' parameter is optional — by default the project's dominant kind. The 'format' parameter is optional too and opens the SPREADSHEET outputs: format='csv' gives, for captable, the holders table (name, type, security, round, shares, % of capital, price per share, amount invested) AND the rounds table in two files — this is what an accountant or a lawyer expects, who read neither Mermaid nor Markdown; for org, a roster block × path × person × role × % ready for an HRIS; for journey, the table phases × steps × emotion × channel × owner; for process, the steps IN EXECUTION ORDER × lane × performer × duration × SLA × cost per case × bottleneck × compliance × successors (with their condition). ⚠️ BPMN 2.0 XML does NOT exist and is not planned: the model has no pools, so a message flow would have no valid place in it: no BPMN export, even an approximate one, is produced. Read-only: it does not modify the schema. The produced FILE(S) are delivered in 'artifacts' (the user has Copy and Download buttons there): no need to copy them into the reply. The result carries in clear the format, the extension, the number of blocks and 'availableFormats' (the other outputs possible for this type, with their audience). ⚠️ 'warnings' lists WHAT THE FILE DOES NOT CARRY, and only for the dimensions this project really holds (e.g. "The Mermaid format does not carry the people assigned to blocks (4 in this project)."). When it is not empty, it is meant for the user, in one sentence; 'availableFormats' names the format that carries the missing dimension if one exists — a Mermaid org chart loses the assignments, the CSV roster carries them. Empty: there is nothing to report. ⚠️ ONE WAY: no tool re-imports these outputs. A ROUND TRIP (export to a repository, edit there, feed back) goes through export_data_model / import_data_model (kind='entity': 'dbml', 'sql-postgres', 'json-schema') or export_arch_diagram / import_arch_diagram (kind='arch': 'mermaid-c4', 'plantuml-c4'). org, process, journey, captable and data-source have NO parser: a file of these types edited elsewhere cannot be fed back. The only complete round trip of the product remains get_full_data → replace_schema (OrgGen JSON).

Input Schema

NameRequiredDescriptionDefault
kindNoType of diagram to export. Optional: by default the project's dominant kind (the one with the most blocks). org / entity / data-source / arch / process / journey → Mermaid (.mmd, rendered natively by GitHub/GitLab/Notion). captable → Markdown (.md: holders table with %, rounds table, + a Mermaid pie chart).
formatNoOutput format. Optional: by default the type's natural format (Mermaid, except captable → Markdown). 'csv' is available for captable (holders table + rounds table, for a spreadsheet or an accountant), org (roster block × person × role × %, for an HRIS), journey (phases × steps × emotion × channel × owner) and process (steps in execution order × lane × performer × duration × SLA × cost × bottleneck × compliance). A format that is unavailable for the type returns an explicit error rather than an empty file — the response then lists the formats actually available.
expectedProjectIdNoUUID of the project targeted by THIS call. ACTUALLY targets this project instead of the session project. Refused without changing anything if access is not granted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / expectedProjectId / description
      Previous value: -"UUID du projet visé par CET appel. Cible RÉELLEMENT ce projet au lieu du projet de session. Refusé sans rien modifier si l'accès n'est pas accordé."New value: +"UUID of the project targeted by THIS call. ACTUALLY targets this project instead of the session project. Refused without changing anything if access is not granted."
    • changedInput schema / properties / format / description
      Previous value: -"Format de sortie. Optionnel : par défaut le format naturel du type (Mermaid, sauf captable → Markdown). 'csv' est disponible pour captable (table des détenteurs + table des tours, pour un tableur ou un expert-comptable), org (roster bloc × personne × rôle × %, pour un SIRH), journey (phases × étapes × émotion × canal × responsable) et process (étapes dans l'ordre d'exécution × couloir × exécutant × durée × SLA × coût × goulot × conformité). Un format indisponible pour le type renvoie une erreur explicite plutôt qu'un fichier vide — la réponse liste alors les formats réellement disponibles."New value: +"Output format. Optional: by default the type's natural format (Mermaid, except captable → Markdown). 'csv' is available for captable (holders table + rounds table, for a spreadsheet or an accountant), org (roster block × person × role × %, for an HRIS), journey (phases × steps × emotion × channel × owner) and process (steps in execution order × lane × performer × duration × SLA × cost × bottleneck × compliance). A format that is unavailable for the type returns an explicit error rather than an empty file — the response then lists the formats actually available."
    • changedInput schema / properties / kind / description
      Previous value: -"Type de diagramme à exporter. Optionnel : par défaut le kind dominant du projet (le plus de cellules). org / entity / data-source / arch / process / journey → Mermaid (.mmd, rendu natif GitHub/GitLab/Notion). captable → Markdown (.md : table des détenteurs avec %, table des tours, + un camembert Mermaid)."New value: +"Type of diagram to export. Optional: by default the project's dominant kind (the one with the most blocks). org / entity / data-source / arch / process / journey → Mermaid (.mmd, rendered natively by GitHub/GitLab/Notion). captable → Markdown (.md: holders table with %, rounds table, + a Mermaid pie chart)."
  2. Changed1 schema field changed
    • changedInput schema / properties / format / description
      Previous value: -"Format de sortie. Optionnel : par défaut le format naturel du type (Mermaid, sauf captable → Markdown). 'csv' est disponible pour captable (table des détenteurs + table des tours, pour un tableur ou un expert-comptable), org (roster bloc × personne × rôle × %, pour un SIRH), journey (phases × étapes × émotion × canal × responsable) et process (étapes dans l'ordre d'exécution × couloir × exécutant × durée × SLA × coût × goulot × conformité). Demander un format indisponible pour le type renvoie une erreur explicite plutôt qu'un fichier vide — la réponse liste alors les formats réellement disponibles."New value: +"Format de sortie. Optionnel : par défaut le format naturel du type (Mermaid, sauf captable → Markdown). 'csv' est disponible pour captable (table des détenteurs + table des tours, pour un tableur ou un expert-comptable), org (roster bloc × personne × rôle × %, pour un SIRH), journey (phases × étapes × émotion × canal × responsable) et process (étapes dans l'ordre d'exécution × couloir × exécutant × durée × SLA × coût × goulot × conformité). Un format indisponible pour le type renvoie une erreur explicite plutôt qu'un fichier vide — la réponse liste alors les formats réellement disponibles."
  3. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations give readOnlyHint/openWorldHint, but the description adds substantial behavior the annotations cannot: files land in 'artifacts' (with Copy/Download), 'availableFormats' and 'warnings' semantics are explained, unavailable-format requests error rather than return empty, and the export is one-way with no re-import. This is rich, non-duplicative disclosure.

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?

The purpose is front-loaded and every section is topically relevant, but the description is very long, uses stacked parentheticals and ⚠️ markers, and re-states enum semantics that already appear verbatim in the input schema. It would lose little if the CSV column enumeration and duplicated format mapping were trimmed.

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

Completeness5/5

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

For a 3-param, no-output-schema export tool, the description covers defaults, error behavior, where files are delivered, what warnings/availableFormats contain, and what cannot be round-tripped. An agent has essentially everything needed to call it correctly.

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

Parameters4/5

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

Schema coverage is 100% (baseline 3), and the description goes beyond it by giving audience-oriented meaning for format='csv' (accountant/lawyer deliverables, HRIS roster, journey table columns) and by explaining the implicit default resolution for both enums. That added context justifies a step above baseline, though much of the enum text is repeated from the schema.

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 ('Exports the current project to a standard, portable text format') and immediately distinguishes scope from the sibling exporters. It names the concrete output mappings (org/entity/... → Mermaid .mmd; captable → Markdown .md), so an agent knows exactly what this produces versus export_data_model or export_arch_diagram.

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?

Explicitly states defaults ('kind' optional = dominant kind; 'format' optional = natural format) and routes the agent elsewhere when needed: round trips go through export_data_model/import_data_model or export_arch_diagram/import_arch_diagram, and org/process/journey/captable/data-source have no parser. It even flags a hard exclusion (no BPMN export, not planned).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.