get_data_source_schemaList the tables and columns available in a connected data source, so you can write correct widget queries. Supported for PostgreSQL, MySQL, SQL Server, Oracle, Aurora, Redshift and Google Sheets.
| Name | Required | Description | Default |
|---|---|---|---|
| table | No | Return only this table. Useful when a database has many tables. | |
| dataSourceId | Yes | Data source id. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, open-world, and non-destructive behavior. The description adds useful context by specifying that the tool lists tables/columns and naming the supported data sources, though it does not discuss edge behavior such as unsupported source errors or output formatting.
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 two sentences with no filler, front-loading the action and purpose before listing supported connectors. Every clause contributes useful 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?
With no output schema, the description still communicates the return concept ('tables and columns') and the supported connector scope. Minor details like error behavior or how the optional table parameter affects the response are not described, but the schema covers optionality and the annotations cover safety.
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 for both parameters, so the description adds little beyond the schema. The description's purpose statement relates generally to data source schema but does not provide extra meaning about the optional table parameter or dataSourceId format.
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 uses a specific verb ('List') and resource ('tables and columns in a connected data source') and includes a clear purpose ('so you can write correct widget queries'). It does not explicitly contrast with sibling tools like get_data_source or list_data_sources, so it lacks explicit sibling 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 phrase 'so you can write correct widget queries' provides a clear when-to-use context, and the supported connector list gives an additional applicability signal. It does not mention exclusions or alternative tools, so it falls short of explicit when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target a distinct resource+action pair, and descriptions explicitly cross-reference related tools (e.g. update_dashboard points to set_dashboard_theme and publish_dashboard). A few pairs remain close enough to cause hesitation—set_widget_layout vs update_widget's position parameter, and get_started vs get_platform_overview—but their descriptions do separate them.
Tool names consistently follow verb_noun snake_case with clear resource nouns like customer, dashboard, widget, and data_source. Minor deviations exist between add_* and create_* for creation operations, and set_* versus update_* for mutations, but the overall pattern is still predictable.
With 42 tools, the surface is much larger than the 16-25 range that already feels heavy, and several onboarding/catalog helpers (get_started, get_platform_overview, list_plans_and_limits, list_supported_data_connectors, list_widget_types) add to the count. Each tool has a distinct job, but the set would benefit from consolidation or splitting into focused sub-servers.
Core lifecycle coverage is strong: dashboards, views, widgets, data sources, customers, and publishing all have create/read/update/delete where relevant, plus test/preview/validation tools. Obvious gaps are customer-user management beyond create/delete (no password reset/update) and no direct way to move a widget between views, but agents can work around these.