Skip to main content
Glama

project_save

Destructive

Queue a native save that backs up and verifies scoped workspace files, confirms only calibrated format-upgrade notices, and checks schematic or PCB save state without keyboard/mouse input.

Instructions

Queue native Save Project; back up and verify the scoped save. Confirm only the exact calibrated format-upgrade notice for workspace copies, never unknown dialogs. Schematic save compares disk circuit/cache; PCB save checks memory plus archive write and needs project_reopen for disk copper verification. No keyboard/mouse.

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": {
      "session": "<session>"
    },
    "name": "project_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
sessionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already flag readOnlyHint=false and destructiveHint=true; the description adds real value beyond them by disclosing that it backs up before saving, verifies the scoped save, refuses unknown dialogs, and operates without keyboard/mouse input. It stops short of describing what happens on failure or how the verification result is reported.

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 core action ('Queue native Save Project'), then layered with verification and dialog policy details. Sentences are dense and jargon-heavy ('exact calibrated format-upgrade notice'), but nearly every clause carries operational information and none is pure filler.

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 destructive, no-output-schema tool the description covers backup, verification strategy, dialog policy, and input modality, which is substantial. It still omits failure behavior and the meaning of the required session argument, leaving gaps an agent would want closed before invoking a destructive save.

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?

The single 'session' parameter has 0% schema description coverage, so the schema contributes nothing and the description must compensate. The phrase 'scoped save' hints that the session scopes the operation, but it never explains what a session identifier is or where to obtain one, leaving the lone required parameter under-explained.

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?

Names a specific verb and resource ('Queue native Save Project') and goes further by distinguishing schematic save (disk circuit/cache comparison) from PCB save (memory plus archive write). It is clearly a save operation and not a read or export, though it never explicitly contrasts itself with siblings like native_apply or project_close.

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?

Gives one concrete routing rule: after a PCB save, use project_reopen to verify disk copper. It also constrains dialog handling to 'only the exact calibrated format-upgrade notice.' However, there is no statement of when to call this versus other write paths such as native_apply or native_commands, so usage is only partially implied.

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