Skip to main content
Glama

Semiotic

by io.github.nteract

Improve an existing chart

improveChart
Read-onlyIdempotent

Diagnose a chart configuration, assess data fit, and propose repairs or variants.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
propsYes
intentNo
componentYes
fieldRolesNoPer-field semantic or exact encoding-role hints used before chart ranking.
identifiersNoFields that identify records and must not be used as visual encodings or measures.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
repairYes
statusYes
variantsYes
componentYes
diagnosticsYes
surfaceVersionYes
evidenceFragmentNo
accessibilityRecommendationNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedOutput schema / properties / evidenceFragment
      Added value: +{
+  "additionalProperties": {},
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}
  2. Changed2 schema fields changed
    • addedInput schema / properties / fieldRoles
      Added value: +{
+  "additionalProperties": {
+    "anyOf": [
+      {
+        "enum": [
+          "identifier",
+          "measure",
+          "dimension",
+          "temporal",
+          "x",
+          "y",
+          "size",
+          "category",
+          "series",
+          "time",
+          "ignore"
+        ],
+        "type": "string"
+      },
+      {
+        "items": {
+          "enum": [
+            "identifier",
+            "measure",
+            "dimension",
+            "temporal",
+            "x",
+            "y",
+            "size",
+            "category",
+            "series",
+            "time",
+            "ignore"
+          ],
+          "type": "string"
+        },
+        "type": "array"
+      }
+    ]
+  },
+  "description": "Per-field semantic or exact encoding-role hints used before chart ranking.",
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}
    • addedInput schema / properties / identifiers
      Added value: +{
+  "description": "Fields that identify records and must not be used as visual encodings or measures.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
  3. Changed5 schema fields changed
    • addedOutput schema / properties / accessibilityRecommendation
      Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "chartContainer": {
+      "additionalProperties": {},
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "location": {
+      "const": "direct-component-props",
+      "type": "string"
+    },
+    "props": {
+      "additionalProperties": {
+        "type": "string"
+      },
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    }
+  },
+  "required": [
+    "location",
+    "props",
+    "chartContainer"
+  ],
+  "type": "object"
+}
    • addedOutput schema / properties / diagnostics
      Added value: +{
+  "items": {},
+  "type": "array"
+}
    • addedOutput schema / properties / repair
      Added value: +{
+  "additionalProperties": {},
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}
    • addedOutput schema / properties / variants
      Added value: +{
+  "items": {},
+  "type": "array"
+}
    • changedOutput schema / required
      Previous value: -[
-  "status",
-  "component",
-  "surfaceVersion"
-]New value: +[
+  "status",
+  "component",
+  "diagnostics",
+  "repair",
+  "variants",
+  "surfaceVersion"
+]
  4. First observed

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive behavior, and the description aligns by saying the tool 'proposes' repairs rather than applying them. It adds some context about assessing data fit and producing variants, but it does not disclose additional operational traits such as limits, prerequisites, or output behavior beyond what the output schema already covers.

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?

A single sentence with front-loaded action verbs and no filler. Every word contributes to the core purpose, and the phrasing is compact without being bloated.

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?

Despite having annotations and an output schema, the definition remains too thin for a 6-parameter tool with nested objects and low schema coverage. An agent still lacks guidance on what component/props should contain, what intent expresses, and how this tool differs in practice from auditChart or explainChart.

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?

The description adds no parameter-level meaning for data, props, component, intent, fieldRoles, or identifiers. Schema description coverage is only 33%, leaving most parameters effectively undocumented, and since coverage is low the description needed to compensate but did not.

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 uses specific verbs—diagnose, assess, propose—and names the resource as a chart configuration, so an agent can tell this is about improving an existing chart. The 'repairs or variants' phrasing distinguishes it from create/explain/audit siblings, but without explicitly naming them, it stops short of full differentiation.

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

Usage Guidelines3/5

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

The description implies the tool is for diagnosing and improving an existing chart rather than creating or explaining one, but it does not state when to prefer it over auditChart or explainChart. There are no explicit when-to-use or when-not-to-use conditions, so the guidance is only implicit.

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

All Semiotic toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation5/5

Each tool addresses a distinct aspect of chart work: creation, auditing, explanation, schema reference, and improvement. There is no overlap in primary purpose, making selection unambiguous.

Naming Consistency5/5

All tool names follow a consistent verb-first camelCase pattern (auditChart, createChart, explainChart, getChartSchema, improveChart). The slight deviation of 'getChartSchema' is still verb-first and aligns with the pattern.

Tool Count5/5

Five tools is well-scoped for a charting focused server, covering the core workflows without redundancy or bloat. Each tool provides a necessary function.

Completeness4/5

The tool surface covers create, analyze, explain, and improve workflows, with schema access for advanced config. Missing explicit update/delete operations is acceptable as charts are typically immutable configurations, and improvements are handled via improveChart.

Resources