Skip to main content
Glama
SynapCores MCP Server

SynapCores MCP Server

Official

Describe a table's columns

describe_table
Read-onlyIdempotent

Returns column names, types, nullability, primary keys, and defaults so you can inspect a table's schema before writing INSERT/UPDATE statements or WHERE filters.

Instructions

Return the column definitions of one table: name, type, nullable, primary_key and default for each column. Use it before writing INSERT/UPDATE statements or WHERE filters, once list_tables has given you the table name; it reads the schema, not the data, unless include_samples=true, which adds up to 5 distinct example values per column (one SELECT DISTINCT per column).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "table": "<table>"
    },
    "name": "describe_table"
  }
}

Input Schema

NameRequiredDescriptionDefault
tableYesTable name, as returned by `list_tables`.
databaseNoDatabase name; omit to use the default database.
include_samplesNotrue = add up to 5 distinct sample values per column (default false).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.0.1
    • changedInput schema / properties / database / description
      Previous value: -"Database name (optional)"New value: +"Database name; omit to use the default database."
    • changedInput schema / properties / include_samples / description
      Previous value: -"Include sample values for each column (default: false)"New value: +"true = add up to 5 distinct sample values per column (default false)."
    • changedInput schema / properties / table / description
      Previous value: -"Table name"New value: +"Table name, as returned by `list_tables`."
  2. First observedv1.0.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description still earns credit by disclosing the schema-versus-data distinction and the cost of include_samples=true (up to 5 distinct values per column, one SELECT DISTINCT per column) — a real behavioral/cost caveat absent from the annotations. It does not cover error behavior or performance on very wide tables.

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?

Two sentences, both front-loaded: the return shape comes first, then the usage trigger and the sampling caveat. Every clause carries information — no restatement of the title or name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, but the description compensates by enumerating the returned fields. All three parameters are covered, the sibling dependency for the table name is stated, and the sampling behavior is qualified, which is everything an agent needs for a three-parameter read tool.

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

Parameters4/5

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

Schema coverage is 100%, so all three parameters are already documented and the baseline is 3. The description adds meaning beyond the schema for include_samples by quantifying the sample size and the per-column query cost, which tells an agent when the flag is expensive. It does not add anything about database resolution beyond what the schema states.

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?

States a specific verb and resource ("Return the column definitions of one table") and enumerates exactly what comes back: name, type, nullable, primary_key, default. That lets an agent distinguish this from list_tables (names only) without opening any schema.

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

Usage Guidelines4/5

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

Gives an explicit trigger — before writing INSERT/UPDATE statements or WHERE filters — and names the prerequisite step ("once `list_tables` has given you the table name"), which sequences it against a sibling. It stops short of stating when not to use it (e.g., for data inspection versus schema inspection), so it is clear guidance rather than exhaustive routing.

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