ScientificFigureLibrary

Overview Schema Source Related Servers Discussions Admin

Plan a direct-intake Working Revision

figure_library_plan_working_revision

Read-onlyIdempotent

Validates user-confirmed image/code intake and returns an immutable Working Revision plan, enabling reliable scientific figure planning without running code.

Instructions

Validate user-confirmed image/code intake and return an immutable Working Revision plan. The operations never calls a model or executes code.

Input Schema

TableJSON Schema

Name	Required	Description
`mode`	No
`tags`	No
`title`	No
`intake`	No
`license`	No
`runtime`	No
`language`	No
`packages`	No
`assetKind`	No
`assessment`	No
`codeAssets`	No
`codeStatus`	No
`plotFamily`	No
`provenance`	No
`templateId`	No
`application`	No	FigureYa-style biological use cases as Markdown; required for new or updated Working revisions. Not visual encodings.
`dataProfile`	No
`description`	No
`visualAssets`	No
`confirmations`	No
`visualProfile`	No
`evidenceAssets`	No
`agentAssessment`	No
`executionStatus`	No
`figureCodeLinks`	No
`referenceAssets`	No
`validationState`	No
`scientificQuestion`	No
`canonicalCodeAssetId`	No
`primaryVisualAssetId`	No
`primaryPreviewOverride`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv0.6.8Sep 12, 2026

addedInput schema / properties / application

Added value: +{
+  "description": "FigureYa-style biological use cases as Markdown; required for new or updated Working revisions. Not visual encodings.",
+  "maxLength": 8000,
+  "type": "string"
+}

addedInput schema / properties / codeAssets / items / properties / rights

Added value: +{
+  "properties": {
+    "attribution": {
+      "maxLength": 4000,
+      "type": "string"
+    },
+    "distribution": {
+      "enum": [
+        "local_only",
+        "public"
+      ],
+      "type": "string"
+    },
+    "license": {
+      "maxLength": 2000,
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "license",
+    "distribution"
+  ],
+  "type": "object"
+}

addedInput schema / properties / evidenceAssets / items / properties / rights

Added value: +{
+  "properties": {
+    "attribution": {
+      "maxLength": 4000,
+      "type": "string"
+    },
+    "distribution": {
+      "enum": [
+        "local_only",
+        "public"
+      ],
+      "type": "string"
+    },
+    "license": {
+      "maxLength": 2000,
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "license",
+    "distribution"
+  ],
+  "type": "object"
+}

addedInput schema / properties / referenceAssets / items / properties / rights

Added value: +{
+  "properties": {
+    "attribution": {
+      "maxLength": 4000,
+      "type": "string"
+    },
+    "distribution": {
+      "enum": [
+        "local_only",
+        "public"
+      ],
+      "type": "string"
+    },
+    "license": {
+      "maxLength": 2000,
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "license",
+    "distribution"
+  ],
+  "type": "object"
+}

addedInput schema / properties / runtime

Added value: +{
+  "properties": {
+    "dependencies": {
+      "items": {
+        "properties": {
+          "assetPath": {
+            "minLength": 1,
+            "type": "string"
+          },
+          "codePath": {
+            "minLength": 1,
+            "type": "string"
+          }
+        },
+        "required": [
+          "codePath",
+          "assetPath"
+        ],
+        "type": "object"
+      },
+      "maxItems": 100,
+      "type": "array"
+    },
+    "entrypoint": {
+      "maxLength": 1000,
+      "minLength": 1,
+      "type": "string"
+    },
+    "inputs": {
+      "items": {
+        "properties": {
+          "assetPath": {
+            "maxLength": 1000,
+            "minLength": 1,
+            "type": "string"
+          },
+          "codePath": {
+            "maxLength": 1000,
+            "minLength": 1,
+            "type": "string"
+          },
+          "required": {
+            "const": true,
+            "type": "boolean"
+          },
+          "role": {
+            "enum": [
+              "example_data",
+              "source_data",
+              "private_reference"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "codePath",
+          "assetPath",
+          "required",
+          "role"
+        ],
+        "type": "object"
+      },
+      "maxItems": 1000,
+      "type": "array"
+    },
+    "output": {
+      "properties": {
+        "mediaType": {
+          "const": "image/png",
+          "type": "string"
+        },
+        "previewPath": {
+          "maxLength": 1000,
+          "minLength": 1,
+          "type": "string"
+        }
+      },
+      "required": [
+        "previewPath",
+        "mediaType"
+      ],
+      "type": "object"
+    },
+    "schema": {
+      "const": "figure-library.runtime-closure.v1",
+      "type": "string"
+    }
+  },
+  "required": [
+    "schema",
+    "entrypoint",
+    "inputs",
+    "output"
+  ],
+  "type": "object"
+}

addedInput schema / properties / visualAssets / items / properties / rights

Added value: +{
+  "properties": {
+    "attribution": {
+      "maxLength": 4000,
+      "type": "string"
+    },
+    "distribution": {
+      "enum": [
+        "local_only",
+        "public"
+      ],
+      "type": "string"
+    },
+    "license": {
+      "maxLength": 2000,
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "license",
+    "distribution"
+  ],
+  "type": "object"
+}

Changed1 schema field changedv0.4.0Sep 1, 2026
- addedInput schema / properties / scientificQuestion
```
Added value: +{
+  "maxLength": 2000,
+  "type": "string"
+}
```
AddedAug 19, 2026

TDQS

A3.6/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds valuable behavioral guarantees: the returned plan is 'immutable' and the operation 'never calls a model or executes code.' This meaningfully clarifies side effects and runtime expectations without contradicting any annotation.

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

Conciseness5/5

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

Two sentences with no filler. The primary purpose is front-loaded, and the behavioral constraint about not calling a model or executing code is a concise, high-value addition. Minor grammar ('operations never calls') does not affect structure.

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 tool with 31 parameters, deeply nested objects, no output schema, and a large sibling family of plan_/apply_ tools, the description only provides top-level purpose and safety. It does not explain what a Working Revision plan contains, how to distinguish direct-intake from restore/bind/publish plans, or what inputs an agent must assemble.

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

Parameters1/5

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

Schema description coverage is only 3%, so the description carries nearly all responsibility for explaining parameters, yet it names none of the 31 fields. 'Image/code intake' only vaguely maps to codeAssets/visualAssets/confirmations, and critical fields like mode, runtime, confirmations, and validationState are left entirely unexplained.

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?

The description states a specific verb and resource: 'Validate user-confirmed image/code intake and return an immutable Working Revision plan.' The title adds 'direct-intake,' which helps narrow scope among many plan_* siblings. It does not explicitly name a sibling alternative, so it stops short of a 5.

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

Usage Guidelines4/5

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

The description clearly implies when to use it: when the user has confirmed image/code intake and a Working Revision plan is needed. It provides no exclusions and does not name alternatives such as figure_library_apply_working_revision or other plan_* tools, so it misses the explicit when/when-not guidance required for a 5.

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

Deploy Server

Plan a direct-intake Working Revision

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools