Skip to main content
Glama
Sign In

ThinAir Data

by co.thinair.data
OverviewDiscussionsAdmin

remove_connection

DestructiveIdempotent

Remove a stored database connection from ThinAir Data by name. This deletes the stored credential, cached schema and schema snapshots, table watches and query firewall rules for that connection, and stops automatic credential renewal. It keeps your query history (7 days), saved queries and audit logs. Your actual database is never touched, nothing is dropped or altered on it; for a few minutes after removal, ThinAir's connection pool may keep or reopen sessions to it using a temporary copy of the connection details, which is then discarded. Call list_connections first if you're unsure of the exact name.

Input Schema

NameRequiredDescriptionDefault
nameYesExact name of the connection to remove, as shown by list_connections.

Output Schema

NameRequiredDescriptionDefault
idNo
nameYes
statusYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • changedOutput schema / additionalProperties
      Previous value: -trueNew value: +{}
  2. Changed1 schema field changed
    • changedOutput schema / properties / status / enum
      Previous value: -[
-  "removed",
-  "not_found"
-]New value: +[
+  "removed",
+  "not_found",
+  "forbidden_scope"
+]
  3. Added

TDQS

A4.4/5.0
Behavior5/5

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

Well beyond the destructiveHint/idempotentHint annotations: it names exactly what is destroyed (credential, cached schema and snapshots, table watches, firewall rules, auto-renewal), what survives (7-day query history, saved queries, audit logs), and that the underlying database is untouched. It even discloses the non-obvious post-removal pool behavior where sessions may persist briefly using a temporary credential copy — precisely the kind of caveat annotations cannot convey.

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?

Front-loaded with the action and its scope, and every sentence adds distinct information (destroyed, preserved, external side effects, fallback). Slightly long-winded in the pool caveat clause, but no redundancy worth cutting.

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?

For a single-parameter destructive tool with an output schema (so return values need no explanation) and full annotation coverage, nothing an agent needs is missing: safety profile, retained data, external impact, and name-resolution path are all present.

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 description coverage is 100%, and the parameter description already says "Exact name of the connection to remove, as shown by list_connections." The description's "by name" and the list_connections pointer largely restate that, so the baseline of 3 applies rather than a higher score.

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 ("Remove a stored database connection from ThinAir Data by name") with explicit scope. The destructive blast radius is enumerated, so an agent can distinguish this from add_connection, test_connection and list_connections 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?

"Call list_connections first if you're unsure of the exact name" gives concrete routing to the right sibling for name resolution. It does not, however, discuss when-not-to-use (e.g. temporarily disabling vs deleting) or how it compares with test_connection for validation, so not a full 5.

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

All ThinAir Data toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources