Skip to main content
Glama
semanticintent

Semantic D1 MCP

Official

validate_database_schema

Validate database schema integrity to detect issues like missing primary keys and orphaned foreign keys in Cloudflare D1 databases.

Instructions

Validate database schema integrity and detect potential issues (missing primary keys, orphaned foreign keys, etc.)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
environmentYesDatabase environment to validate

Implementation Reference

  • Registration of the 'validate_database_schema' MCP tool, including name, description, and input schema definition.
    {
    	name: 'validate_database_schema',
    	description:
    		'Validate database schema integrity and detect potential issues (missing primary keys, orphaned foreign keys, etc.)',
    	inputSchema: {
    		type: 'object',
    		properties: {
    			environment: {
    				type: 'string',
    				enum: ['development', 'staging', 'production'],
    				description: 'Database environment to validate',
    			},
    		},
    		required: ['environment'],
    	},
    },
  • Handler method in MCP server that processes tool calls for 'validate_database_schema' by invoking the ValidateSchemaUseCase.
    private async handleValidateSchema(args: unknown) {
    	const { environment } = args as { environment: string };
    
    	const result = await this.validateSchemaUseCase.execute({
    		environment: parseEnvironment(environment),
    	});
    
    	return {
    		content: [
    			{
    				type: 'text',
    				text: JSON.stringify(result, null, 2),
    			},
    		],
    	};
  • Execute method of ValidateSchemaUseCase that fetches the database schema (with caching), performs validation, and constructs the response.
    async execute(request: ValidateSchemaRequest): Promise<SchemaValidationResponse> {
    	const environment = request.environment;
    
    	// Observable: Cache key based on environment
    	const cacheKey = `schema:${environment}`;
    
    	// Check cache first (avoid repeated API calls)
    	let schema = await this.cache.get<DatabaseSchema>(cacheKey);
    
    	if (!schema) {
    		// Fetch schema from repository
    		const databaseId = this.databaseConfig.getDatabaseId(environment);
    		schema = await this.repository.fetchDatabaseSchema(databaseId);
    
    		// Cache for future requests (10-minute TTL)
    		await this.cache.set(cacheKey, schema, ValidateSchemaUseCase.CACHE_TTL_SECONDS);
    	}
    
    	// Validate schema and collect issues
    	const issues = this.validateSchema(schema);
    
    	// Count issues by severity
    	const errorCount = issues.filter((i) => i.severity === ValidationSeverity.ERROR).length;
    	const warningCount = issues.filter((i) => i.severity === ValidationSeverity.WARNING).length;
    	const infoCount = issues.filter((i) => i.severity === ValidationSeverity.INFO).length;
    
    	return {
    		databaseName: schema.name,
    		environment: schema.environment,
    		isValid: errorCount === 0,
    		errorCount,
    		warningCount,
    		infoCount,
    		issues,
    		validatedAt: new Date(),
    	};
    }
  • Core schema validation logic implementing checks for missing primary keys, orphaned/invalid foreign keys, missing indexes, and nullable FK issues.
    private validateSchema(schema: DatabaseSchema): ValidationIssue[] {
    	const issues: ValidationIssue[] = [];
    
    	// Validate each table
    	for (const table of schema.tables) {
    		// Check for tables without primary key
    		const hasPrimaryKey = table.columns.some((col) => col.isPrimaryKey);
    		if (!hasPrimaryKey) {
    			issues.push({
    				severity: ValidationSeverity.WARNING,
    				category: 'Missing Primary Key',
    				message: `Table '${table.name}' has no primary key`,
    				table: table.name,
    				details: {
    					recommendation: 'Add a primary key column for better query performance and data integrity',
    				},
    			});
    		}
    
    		// Check for orphaned foreign keys (references non-existent tables)
    		for (const fk of table.foreignKeys) {
    			const referencedTableExists = schema.tables.some((t) => t.name === fk.referencesTable);
    			if (!referencedTableExists) {
    				issues.push({
    					severity: ValidationSeverity.ERROR,
    					category: 'Orphaned Foreign Key',
    					message: `Foreign key references non-existent table '${fk.referencesTable}'`,
    					table: table.name,
    					column: fk.column,
    					details: {
    						referencedTable: fk.referencesTable,
    						referencedColumn: fk.referencesColumn,
    					},
    				});
    			} else {
    				// Check if referenced column exists
    				const referencedTable = schema.tables.find((t) => t.name === fk.referencesTable);
    				const referencedColumnExists = referencedTable?.columns.some(
    					(col) => col.name === fk.referencesColumn,
    				);
    				if (!referencedColumnExists) {
    					issues.push({
    						severity: ValidationSeverity.ERROR,
    						category: 'Invalid Foreign Key',
    						message: `Foreign key references non-existent column '${fk.referencesColumn}' in table '${fk.referencesTable}'`,
    						table: table.name,
    						column: fk.column,
    						details: {
    							referencedTable: fk.referencesTable,
    							referencedColumn: fk.referencesColumn,
    						},
    					});
    				}
    			}
    		}
    
    		// Check for tables with no indexes (potential performance issue)
    		if (table.indexes.length === 0 && table.type === 'table') {
    			issues.push({
    				severity: ValidationSeverity.INFO,
    				category: 'No Indexes',
    				message: `Table '${table.name}' has no indexes`,
    				table: table.name,
    				details: {
    					recommendation: 'Consider adding indexes on frequently queried columns',
    				},
    			});
    		}
    
    		// Check for nullable foreign key columns (potential data integrity issue)
    		for (const fk of table.foreignKeys) {
    			const fkColumn = table.columns.find((col) => col.name === fk.column);
    			if (fkColumn?.isNullable && fk.onDelete !== 'SET NULL') {
    				issues.push({
    					severity: ValidationSeverity.WARNING,
    					category: 'Nullable Foreign Key',
    					message: `Nullable foreign key column '${fk.column}' should have ON DELETE SET NULL`,
    					table: table.name,
    					column: fk.column,
    					details: {
    						currentOnDelete: fk.onDelete,
    						recommendation: 'SET NULL',
    					},
    				});
    			}
    		}
    	}
    
    	return issues;
    }
  • Input schema definition for the 'validate_database_schema' tool.
    inputSchema: {
    	type: 'object',
    	properties: {
    		environment: {
    			type: 'string',
    			enum: ['development', 'staging', 'production'],
    			description: 'Database environment to validate',
    		},
    	},
    	required: ['environment'],
    },

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations provided, the description carries full responsibility for disclosing behavioral traits. It states what the tool detects but does not mention whether it is read-only, whether it modifies data, what the output format is, or if it requires special permissions. This is a meaningful gap for a validation tool that could potentially be expected to run side-effect-free checks.

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?

The description is a single sentence that front-loads the primary action ('Validate database schema integrity') and then provides concrete examples to clarify scope. There is no redundant wording or filler, and every part of the sentence contributes useful information.

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?

The tool has no output schema and no annotations, yet the description does not explain what the result looks like or how issues are reported. Given the presence of sibling tools with overlapping purposes, the description also fails to clarify the tool's unique position. While the single parameter is well-documented, the lack of return-value or behavioral context leaves the description incomplete.

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

Parameters3/5

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

The input schema has 100% schema description coverage: the single parameter 'environment' is fully described with an enum of valid values and a clear meaning. The description adds no additional semantic detail beyond the schema, so the baseline score of 3 is appropriate.

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 description uses a specific verb ('Validate') with a clear resource ('database schema') and enumerates concrete examples of what it checks (missing primary keys, orphaned foreign keys). This distinguishes it from related sibling tools like analyze_database_schema and suggest_schema_optimizations, which imply broader or different scopes.

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

Usage Guidelines2/5

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

The description provides no explicit guidance on when to use this tool versus alternatives such as analyze_database_schema or compare_schemas. It does not mention any exclusions, prerequisites, or scenarios where another tool would be preferred, leaving the agent to infer usage solely from the tool name and purpose.

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