Skip to main content
Glama
influxdata

InfluxDB MCP Server

Official
by influxdata
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

investigate_database

Discover tables and schemas in a database, then optionally sample recent rows with bounded reads to understand its structure before querying.

Instructions

Discover tables and schemas in a database, optionally sampling recent rows from each table with bounded reads.

Input Schema

NameRequiredDescriptionDefault
dbYesDatabase name to investigate
maxTablesNo
includeSamplesNoWhether to include recent sample rows
sampleWindowHoursNoLook back this many hours from investigation start.
sampleRowsPerTableNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.0.0
    • changedInput schema / properties / maxTables / type
      Previous value: -"number"New value: +"integer"
    • changedInput schema / properties / sampleRowsPerTable / type
      Previous value: -"number"New value: +"integer"
    • addedInput schema / properties / sampleWindowHours
      Added value: +{
+  "default": 24,
+  "description": "Look back this many hours from investigation start.",
+  "maximum": 8760,
+  "minimum": 1,
+  "type": "integer"
+}
  2. First observedv1.4.1-test.1

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. 'Bounded reads' usefully signals that sampling is capped rather than a full table scan, which is real behavioral information, but there is no disclosure of read-only safety, required permissions, or the cost/latency of sampling many tables at once.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single well-packed sentence with the core capability front-loaded and no filler. It could be marginally tighter by separating the discovery mode from the sampling mode, but nothing in it is wasted.

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

Completeness3/5

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

For a five-parameter exploration tool with no output schema and no annotations, the description should say what comes back (table names, column schemas, sample shape) and what maxTables/default-20 truncation implies. It covers the two operating modes but leaves the result contract and partial-coverage caveats unstated.

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?

Schema coverage is 60%: db, includeSamples, and sampleWindowHours are documented inline, while maxTables and sampleRowsPerTable are not. The description supplies partial compensation by saying sampling happens 'from each table' and is 'bounded', hinting at per-table limits, but it never explains what maxTables truncation means for completeness of the discovery result.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Discover tables and schemas in a database', plus an optional sampling mode. An agent can tell it is an exploration tool rather than a query executor, but it never names list_tables or describe_table, which occupy adjacent ground in the sibling list.

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

Usage Guidelines3/5

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

The phrase 'optionally sampling recent rows' implies when to set includeSamples, but there is no explicit when-to-use versus list_tables, describe_table, or query_sql, and no guidance on when sampling is wasteful. Usage must be inferred from the name and the word 'investigate'.

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

Deploy Server

Other Tools