Skip to main content
Glama

Pin a branch state

argon_pin_create

Pin a branch state under a unique name to preserve immutable dataset references through garbage collection and resets, enabling identical sandbox inputs for every eval run.

Instructions

Pin a branch state under a name: a named, immutable dataset reference that survives garbage collection and resets forever. Pin an eval dataset once, then fork sandboxes from the pin for every run and get identical input state.

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": {
      "project": "<project>",
      "name": "<name>"
    },
    "name": "argon_pin_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
lsnNoLSN to pin (default: current head)
nameYesPin name, unique per project
noteNoFree-form note
branchNoBranch to pin (default: main)
projectYesProject name

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.8.1

TDQS

A3.8/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false; the description corroborates this by framing the pin as a durable, additive reference rather than a mutation of existing state. It adds real behavioral value beyond the annotations: immutability, survival of garbage collection, and persistence across resets. It does not say what happens if the name is already taken, which matters for a non-idempotent create.

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, zero filler. The identity of the resource is front-loaded and the motivating use case follows, so an agent gets the definition before the rationale.

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

Completeness4/5

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

For a five-parameter create tool with full schema coverage and annotation coverage, the description supplies the durability and immutability semantics that structured fields cannot express, and no output schema means return values need not be explained. The remaining gap is collision/error behavior on a duplicate name for a non-idempotent operation.

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%, with defaults for lsn (current head) and branch (main) and a uniqueness note on name already documented in the schema. The description adds no parameter-level detail such as format of lsn, name constraints, or how note is surfaced, so it stays at the baseline.

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?

"Pin a branch state under a name" gives a specific verb and resource, and the appositive "a named, immutable dataset reference that survives garbage collection and resets forever" defines exactly what a pin is. It stops short of differentiating the pin from the closely related snapshot/sandbox siblings, so an agent must infer which reference type to create.

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?

"Pin an eval dataset once, then fork sandboxes from the pin for every run" supplies one concrete scenario that implies when to reach for this tool. There is no explicit when-not guidance, no prerequisites, and no named alternative (e.g. snapshot vs pin) to steer the agent away from a wrong choice.

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