tabletalk
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask_databaseA | Ask the database a question in plain language. The agent writes and runs the SQL itself. Reuse thread_id for follow-up questions. Returns the answer and the SQL used. |
| run_sqlA | Run one read-only SELECT directly and return the rows as text. |
| describe_schemaA | List tables, columns, foreign keys and sample rows. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: ask_database handles natural language queries, run_sql executes direct SQL, and describe_schema exposes metadata. Even though ask_database and run_sql both query data, their interaction modes are different and descriptions make the boundaries explicit.
All tool names follow a consistent verb_noun pattern in snake_case: ask_database, run_sql, describe_schema. This makes the naming predictable and easy to extend.
Three tools is a compact, well-scoped set for a database query assistant. Each tool serves a necessary role—schema discovery, natural language querying, and direct SQL access—without redundancy or bloat.
For its stated read-only querying purpose, the tool surface is complete: describe_schema enables understanding the data, ask_database handles plain-language questions, and run_sql provides raw querying capability. No obvious dead ends or missing operations exist within this scope.