Skip to main content
Glama
Sign In

Connections

by icu.connections
OverviewDiscussionsAdmin

Script Vault: save a reusable instrument

connections_script_save
Destructive

Save a small script instrument (enumerator / tracer / parity-differ) into this company's Script Vault, so any future session finds it via connections_search_catalog and runs it LOCALLY through the local MCP's script_run. Upserts per tool_name and stores language (javascript/Node by default; bun for Bun APIs or TypeScript imports). Scripts NEVER execute on this server - they are stored and served only. Size is tier-gated by the Pass plan (free 16KB, Pro 64KB, Business and Business Plus 1MB): an over-limit save is rejected with upgrade info, and after a downgrade an over-limit stored script stays saved but LOCKS until upgrade. Write description for semantic search: what the instrument finds/does and when to reach for it - an undiscoverable script is a wasted one.

Input Schema

NameRequiredDescriptionDefault
codeYesThe full script text. Runs locally; args arrive via CONNECTIONS_SCRIPT_ARGS (JSON env).
nameNoHuman display name (defaults to tool_name).
tagsNoOptional tags (e.g. ['sweep','i18n']).
personNoLinked person to run this call as (first name). Omit to run as the connection's holder.
projectNoWorkspace to run this call in (id or name).
languageNoDefault 'javascript' (run with node).
tool_nameYesStable slug, [a-z0-9_]+ (e.g. i18n_freeze_tracer). Same name = update in place.
parametersNoOptional docs of the args the script accepts ({ args: [{name, description}] }).
descriptionYesWhat it enumerates/answers, its parameters, and when to reach for it - this text IS the search index.
destructiveNotrue when running it mutates things (default false - instruments should enumerate, not mutate).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / person
      Added value: +{
+  "description": "Linked person to run this call as (first name). Omit to run as the connection's holder.",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / project
      Added value: +{
+  "description": "Workspace to run this call in (id or name).",
+  "type": "string"
+}
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=true; the description adds substantial behavior beyond that: upsert-per-tool_name overwrite semantics, scripts never execute server-side, exact per-tier size limits (16KB/64KB/1MB), rejection with upgrade info, and post-downgrade lock-in-place behavior. That is precisely the operational detail an agent cannot infer from the annotation flags.

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 in the first clause, then constraints and the description-writing tip. Dense but essentially fluff-free; the parenthetical tier list and the closing admonition are the only parts that could be tightened.

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 10-parameter mutation tool with full schema coverage and no output schema, this covers the storage model, size limits, failure modes, and cross-tool execution path. The only residual gap is what the call returns on success (slug confirmation vs. record id), which is minor.

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 the baseline is 3, but the description adds meaning beyond the schema: `language` is explained as 'bun for Bun APIs or TypeScript imports' versus Node, and the tier limits attach a concrete size constraint to `code`. It does not explain `person`, `project`, or the interaction between the write-time `destructive` flag and the tool-level destructiveHint.

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?

Specific verb + resource + destination: 'Save a small script instrument (enumerator/tracer/parity-differ) into this company's Script Vault'. It also names the downstream lifecycle (discoverable via connections_search_catalog, executed locally via script_run), which cleanly separates it from connections_script_get/delete/restore siblings.

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 clear when-to-use context (so future sessions can find and run the script) plus an explicit failure condition (over-limit saves are rejected with upgrade info). It stops short of routing among the script siblings — nothing tells the agent to call connections_script_get first before overwriting an existing tool_name, or that connections_script_restore is the recovery path.

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

All Connections 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