一个用于 Teradata 数据库的模型上下文协议 (MCP) 服务器，支持 OAuth 2.1 身份验证、多种身份验证机制 (TD2, LDAP, Kerberos) 以及交互式数据可视化。
多种身份验证机制 — TD2 (默认), LDAP, Kerberos, 通过 Teradata LOGMECH 使用 JWT
OAuth 2.1 — 集成 Keycloak，支持 JWT 验证和基于作用域 (scope) 的授权
受保护资源元数据 (符合 RFC 9728 标准)
交互式可视化 — 基于 ECharts 的 MCP 应用，支持 19 种图表类型
连接弹性 — 具备指数退避算法的自动重试机制
非阻塞 I/O — 所有数据库操作均通过 asyncio.to_thread() 运行
工具级 QueryBand — 用于 Teradata 工作负载管理的审计追踪
Related MCP server: Teradata MCP Server
query — 执行 SQL 查询，返回纯表格结果
visualize_query — 执行 SQL 并通过 MCP 应用渲染交互式 ECharts 图表
list_db — 列出所有数据库
list_tables — 列出数据库中的表/视图
show_tables_details — 显示表的列名和类型
list_missing_values — 统计各列的 NULL 值数量
list_negative_values — 统计各列的负值数量
list_distinct_values — 统计各列的不同类别数量
standard_deviation — 计算某列的平均值和标准差
visualize_query 工具在 MCP 客户端中将结果渲染为交互式图表。
分类 | 图表 |
柱状图 | 基础、分组、堆叠、水平、排序、瀑布、圆角、极坐标 |
折线图 | 基础、平滑、面积、堆叠面积、阶梯 |
饼图 | 饼图、环形图、玫瑰图 / 南丁格尔玫瑰图 |
散点图 | 散点图、气泡图 |
混合图 | 柱状图 + 折线图 |
git clone https://github.com/arturborycki/mcp-teradata.git
cd mcp-teradata
uv syncuv run teradata-mcp "teradatasql://user:password@host/database"或通过环境变量：
export DATABASE_URI="teradatasql://user:password@host/database"
uv run teradata-mcp添加到你的 claude_desktop_config.json 中：
{
"mcpServers": {
"teradata": {
"command": "uv",
"args": [
"--directory", "/path/to/mcp-teradata",
"run", "teradata-mcp"
],
"env": {
"DATABASE_URI": "teradatasql://user:password@host/database"
}
}
}
}{
"mcpServers": {
"teradata": {
"command": "uv",
"args": [
"--directory", "/path/to/mcp-teradata",
"run", "teradata-mcp"
],
"env": {
"DATABASE_URI": "teradatasql://@host/database",
"DB_LOGMECH": "LDAP",
"DB_LOGDATA": "authcid=ldap_user password=ldap_password"
}
}
}
}authcid 格式取决于 LDAP 目录：
目录 | 格式 |
Active Directory (Simple Bind) |
|
Active Directory (DIGEST-MD5) |
|
OpenLDAP / Sun DS |
|
{
"mcpServers": {
"teradata": {
"command": "uv",
"args": [
"--directory", "/path/to/mcp-teradata",
"run", "teradata-mcp"
],
"env": {
"DATABASE_URI": "teradatasql://@host/database",
"DB_LOGMECH": "KRB5"
}
}
}
}{
"mcpServers": {
"teradata": {
"command": "uv",
"args": [
"--directory", "/path/to/mcp-teradata",
"run", "teradata-mcp"
],
"env": {
"DATABASE_URI": "teradatasql://user:password@host/database",
"OAUTH_ENABLED": "true",
"KEYCLOAK_URL": "https://your-keycloak.example.com",
"KEYCLOAK_REALM": "teradata-realm",
"KEYCLOAK_CLIENT_ID": "teradata-mcp",
"KEYCLOAK_CLIENT_SECRET": "your-secret",
"OAUTH_RESOURCE_SERVER_URL": "https://your-mcp-server.example.com"
}
}
}
}变量 | 描述 | 默认值 |
| Teradata 连接 URL ( | — |
| 身份验证机制: |
|
| LDAP/JWT 凭据 (例如 | — |
| TLS 模式: | — |
| 启用传输加密 |
|
变量 | 描述 | 默认值 |
| 最大重连尝试次数 |
|
| 初始退避延迟（秒） |
|
| 最大退避延迟（秒） |
|
变量 | 描述 | 默认值 |
| 传输方式: |
|
| HTTP 传输的绑定地址 |
|
| HTTP 传输的端口 |
|
| streamable-http 的路径 |
|
变量 | 描述 | 默认值 |
| 启用 OAuth 身份验证 |
|
| Keycloak 服务器 URL | — |
| Keycloak 领域名称 | — |
| OAuth 客户端 ID | — |
| OAuth 客户端密钥 | — |
| 资源服务器 URL | — |
| 所需作用域（逗号分隔） | — |
| 验证令牌受众 |
|
| 验证令牌作用域 |
|
| OAuth URL 强制 HTTPS |
|
| CORS 允许的来源 |
|
作用域 | 描述 |
| 数据库资源的读取权限 |
| 数据库资源的写入权限 |
| 执行 SQL 查询权限 |
| 管理权限 |
| 模式管理操作权限 |
传输方式 | OAuth | 发现端点 | 使用场景 |
stdio | N/A | N/A | Claude Desktop, CLI 客户端 |
SSE | 支持 | 可用 | Web 应用程序 |
Streamable HTTP | 支持 | 可用 | API 集成 |
发现端点（启用 OAuth 时）：
/.well-known/oauth-protected-resource — RFC 9728 元数据
/.well-known/mcp-server-info — MCP 功能信息
/health — 健康检查
docker compose up -ddocker compose -f docker-compose.oauth.yml up -duv build数据库连接问题：
验证 DATABASE_URI 格式: teradatasql://user:pass@host/database
检查到 Teradata 服务器的网络连通性
对于 LDAP：确保正确设置了 DB_LOGMECH=LDAP 和 DB_LOGDATA
连接问题会自动重试（可通过 DB_MAX_RETRIES 配置）
LDAP 身份验证失败：
验证 Teradata 服务器已在 TDGSS 中配置了 LDAP
检查 authcid 格式是否与你的目录类型匹配
转义密码中的特殊字符 (@ → \@, 空格 → 使用引号)
权限拒绝错误：
验证用户是否拥有所需的 OAuth 作用域
检查 Keycloak 角色分配
visualize_query 需要 teradata:query 作用域（不仅仅是 teradata:read）
调试日志：
export LOG_LEVEL=DEBUG
uv run teradata-mcpMIT 许可证。详情请参阅 LICENSE。
List all databases in the Teradata system
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states it's a listing operation, implying it's read-only, but doesn't specify whether it requires authentication, has rate limits, returns paginated results, or what format the output takes. This leaves significant gaps for a tool that interacts with a database system.
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?
The description is a single, clear sentence with no wasted words. It's front-loaded with the core action and resource, making it easy to parse quickly. Every word earns its place by conveying essential information.
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?
Given the complexity of interacting with a Teradata system and the lack of annotations or output schema, the description is incomplete. It doesn't address behavioral aspects like authentication needs, output format, or error handling, which are critical for an agent to use this tool effectively in a database context.
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?
The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately doesn't discuss parameters, focusing instead on the tool's purpose. A baseline of 4 is applied since no parameters exist to document.
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?
The description clearly states the action ('List all') and resource ('databases in the Teradata system'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'list_tables' or 'show_tables_details', which might list different resources in the same system.
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?
The description provides no guidance on when to use this tool versus alternatives like 'list_tables' or 'show_tables_details'. It lacks context about use cases, prerequisites, or exclusions, leaving the agent to infer usage based on tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
How many distinct categories are there for column in the table
| Name | Required | Description | Default |
|---|---|---|---|
| table_name | Yes | Table name to list |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions counting distinct categories but doesn't specify if this is a read-only operation, performance implications, error handling, or output format. This leaves significant gaps for a tool that likely queries data.
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?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded and to the point, though it could be slightly more structured to clarify ambiguities.
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?
Given no annotations and no output schema, the description is incomplete. It doesn't explain what 'distinct categories' means, how the column is selected, or what the return value looks like (e.g., count, list). For a tool with one parameter but unclear behavior, this is inadequate.
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?
The input schema has 100% description coverage, with 'table_name' clearly documented. The description adds minimal value beyond the schema by implying a column is involved but doesn't specify which column or provide additional context. Baseline 3 is appropriate as the schema handles the parameter documentation.
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?
The description states the tool counts distinct categories for a column in a table, which is a clear purpose. However, it doesn't specify which column or how it determines 'categories,' making it somewhat vague. It distinguishes from siblings like list_tables or query but could be more specific.
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?
No guidance is provided on when to use this tool versus alternatives such as list_missing_values or standard_deviation. The description implies usage for counting distinct categories but doesn't mention prerequisites, exclusions, or specific scenarios, leaving the agent without clear direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
What are the top features with missing values in a table
| Name | Required | Description | Default |
|---|---|---|---|
| table_name | Yes | Table name to list |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does but lacks details on how it works—such as how 'top features' are determined, whether results are sorted, if there are limits on output, or what the return format looks like. This is inadequate for a tool with no structured behavioral hints.
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?
The description is a single, clear sentence that directly states the tool's purpose without unnecessary words. It's front-loaded and efficiently communicates the core function, making it highly concise and well-structured.
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?
Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what 'top features' means, how missing values are identified, or what the output looks like. For a tool with no structured behavioral or output information, this leaves significant gaps in understanding.
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?
The schema description coverage is 100%, with the parameter 'table_name' fully documented in the input schema. The description doesn't add any additional meaning or context beyond what the schema provides, such as examples or constraints. This meets the baseline for high schema coverage.
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?
The description clearly states the tool's purpose: identifying top features with missing values in a table. It specifies the verb 'list' and resource 'features with missing values', making it understandable. However, it doesn't explicitly differentiate from sibling tools like list_distinct_values or list_negative_values, which prevents a perfect score.
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?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context for selecting it over siblings like query or list_tables, or any exclusions. This leaves the agent with minimal usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
How many features have negative values in a table
| Name | Required | Description | Default |
|---|---|---|---|
| table_name | Yes | Table name to list |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states what the tool does but doesn't describe how it behaves: it doesn't specify what constitutes a 'feature' (e.g., columns, rows), how negative values are detected (e.g., numeric types only), what the output format is (e.g., a count number, a list), or any error handling. For a tool with no annotations, this leaves significant gaps in understanding its operation.
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?
The description is a single, clear sentence that directly states the tool's purpose without unnecessary words. It's front-loaded with the core functionality ('How many features have negative values'), making it efficient and easy to parse. There's no wasted information, and it appropriately sized for a simple tool.
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?
Given the tool's complexity (analytical operation on tables), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what 'features' are, how the count is returned, or any behavioral details like error cases. For a tool that performs data analysis, more context is needed to use it effectively, especially without structured support from annotations or output schema.
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?
The input schema has 100% description coverage, with the parameter 'table_name' documented as 'Table name to list'. The description adds minimal value beyond this, as it mentions 'in a table' which aligns with the schema but doesn't provide additional context like table format requirements or examples. With high schema coverage, the baseline is 3, and the description doesn't significantly enhance parameter understanding.
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?
The description clearly states the tool's purpose: to count how many features have negative values in a table. It specifies the verb 'list' (though 'count' would be more precise) and the resource 'features with negative values in a table'. However, it doesn't explicitly differentiate from siblings like list_missing_values or list_distinct_values, which perform similar analytical functions on tables.
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?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like list_missing_values for missing data analysis or query for more complex filtering. There's no context about prerequisites, such as requiring the table to exist or have numeric features, nor any exclusions or recommendations for specific use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List tables in a database
| Name | Required | Description | Default |
|---|---|---|---|
| db_name | Yes | Database name to list |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure but offers minimal information. It doesn't specify whether this is a read-only operation, what permissions are required, how results are formatted (e.g., pagination, sorting), or potential limitations. The description is too basic for a tool that interacts with databases.
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?
The description is extremely concise with a single, clear sentence that states the core functionality without any wasted words. It's front-loaded and efficiently communicates the essential purpose, making it easy for an agent to parse quickly.
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?
Given the lack of annotations and output schema, the description is insufficiently complete. It doesn't explain what the tool returns (e.g., a list of table names, metadata), potential errors, or behavioral nuances. For a database tool with siblings offering similar functionality, more context is needed to guide proper usage.
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?
The schema description coverage is 100%, with the single parameter 'db_name' clearly documented in the schema. The description adds no additional parameter semantics beyond what's already in the schema, so it meets the baseline score of 3 for adequate but not additive documentation.
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?
The description clearly states the verb ('List') and resource ('tables in a database'), making the purpose immediately understandable. It distinguishes from siblings like 'list_db' (which lists databases) and 'show_tables_details' (which provides detailed table information), though it doesn't explicitly mention these distinctions in the text.
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?
The description provides no guidance on when to use this tool versus alternatives like 'show_tables_details' or 'query'. It doesn't mention prerequisites, context, or exclusions, leaving the agent to infer usage based solely on the tool name and basic purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Executes a SQL query against the Teradata database
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | SQL query to execute that is a dialect of Teradata SQL |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure but offers minimal information. It states the tool executes SQL queries but doesn't cover critical aspects like whether it's read-only or destructive, authentication requirements, rate limits, error handling, or result formats. This leaves significant gaps for a database interaction tool.
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?
The description is extremely concise with a single sentence that directly states the tool's function without any unnecessary words. It's front-loaded with the core purpose and appropriately sized for what it communicates, making it efficient and easy to parse.
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?
Given the complexity of executing SQL queries against a database, the description is incomplete. With no annotations, no output schema, and minimal behavioral transparency, it fails to address important aspects like result handling, error conditions, security implications, or performance considerations. The description alone is insufficient for safe and effective tool usage.
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?
The description doesn't add meaningful parameter semantics beyond what the input schema already provides. With 100% schema description coverage, the schema fully documents the single 'query' parameter. The description's mention of 'Teradata SQL' slightly reinforces the schema's 'dialect of Teradata SQL' but doesn't provide additional syntax, format, or constraint details.
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?
The description clearly states the action ('executes') and target resource ('SQL query against the Teradata database'), providing specific verb+resource pairing. However, it doesn't distinguish this tool from potential sibling tools that might also execute queries or interact with the database in similar ways, preventing a perfect score.
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?
No guidance is provided about when to use this tool versus alternatives. The description doesn't mention prerequisites, appropriate contexts, or exclusions, leaving the agent without usage direction. Sibling tools like list_tables or show_tables_details might be related, but no comparison is made.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Show detailed information about a database tables
| Name | Required | Description | Default |
|---|---|---|---|
| db_name | Yes | Database name to list | |
| table_name | No | Table name to list |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action but doesn't describe traits like whether it's read-only, requires permissions, returns structured data, or has limitations. This leaves significant gaps in understanding how the tool behaves beyond its basic function.
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?
The description is a single, straightforward sentence that efficiently conveys the core purpose without unnecessary words. It's front-loaded and to the point, though it could be slightly more structured by hinting at output or usage context.
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?
Given no annotations and no output schema, the description is incomplete for a tool that likely returns complex table details. It doesn't explain what 'detailed information' includes, such as schema, row counts, or metadata, leaving the agent guessing about the return format and utility.
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?
The input schema has 100% description coverage, documenting both parameters clearly. The description adds no additional meaning beyond the schema, such as explaining the scope of 'detailed information' or how parameters interact. Baseline 3 is appropriate as the schema handles parameter documentation adequately.
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?
The description clearly states the verb 'show' and the resource 'detailed information about database tables', making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'list_tables', which might list tables without details, leaving some ambiguity about uniqueness.
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?
The description provides no guidance on when to use this tool versus alternatives such as 'list_tables' or 'query'. It lacks context about prerequisites, exclusions, or specific scenarios where detailed table information is needed, offering minimal usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
What is the mean and standard deviation for column in table?
| Name | Required | Description | Default |
|---|---|---|---|
| table_name | Yes | Table name to list | |
| column_name | Yes | Column name to list |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but lacks behavioral details. It doesn't disclose if this is a read-only operation, whether it requires specific permissions, how it handles errors, or what the output format is. The description only states what it calculates, not how it behaves.
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?
The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It's appropriately sized and front-loaded, though it could be slightly more structured for clarity.
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?
Given no annotations and no output schema, the description is incomplete. It doesn't explain the return values, error handling, or behavioral traits needed for a statistical calculation tool, leaving significant gaps in understanding.
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 description coverage is 100%, so the schema already documents both parameters. The description implies these parameters are used to identify the target column but adds no syntax, format, or validation details beyond what the schema provides, meeting the baseline for high coverage.
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?
The description states the tool calculates 'mean and standard deviation for column in table', which provides a specific verb (calculate) and resource (column in table). However, it doesn't distinguish from siblings like 'list_distinct_values' or 'list_missing_values' that also analyze columns, making the purpose somewhat vague regarding differentiation.
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?
The description offers no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, exclusions, or compare to siblings like 'query' for more complex analyses, leaving the agent with no usage context.
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.
v0.1.0list_dblist_distinct_valueslist_missing_valueslist_negative_valueslist_tablesqueryshow_tables_detailsstandard_deviationScored across 8 tools
The tools have some overlap in purpose, particularly between list_tables and show_tables_details, which both deal with table information, and between the various 'list_' statistical tools (distinct_values, missing_values, negative_values, standard_deviation) that all analyze table columns. However, the descriptions help clarify their specific focuses, such as distinct categories vs. missing values vs. negative values, preventing complete confusion.
The naming is mostly consistent with a verb_noun pattern, using 'list_' for most tools (list_db, list_distinct_values, etc.) and other clear verbs like 'query' and 'show_tables_details'. The only minor deviation is 'standard_deviation', which uses a noun phrase instead of a verb, but it still fits the overall readable style without mixing conventions like camelCase.
With 8 tools, the count is well-scoped for a database analysis server. Each tool earns its place by covering distinct aspects like database listing, table listing, SQL querying, and statistical analysis, without being too thin or overloaded for the apparent purpose of interacting with Teradata systems.
The tool surface has notable gaps for a database server. While it covers listing databases and tables, querying, and some statistical analysis, it lacks core CRUD operations like create, update, or delete for databases or tables. This could cause agent failures when trying to modify data, but the existing tools support basic querying and inspection workflows.
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Query Postgres, MySQL, SQL Server, Oracle, BigQuery, ClickHouse and Redshift from your AI client.
Securely query and analyze business data, dashboards, projections, alerts, and knowledge.
Query your databases and build dashboards, Streamlit apps and reports your team logs in to.
