Skip to main content
Glama
Mibayy

token-savior

by Mibayy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

switch_project

Idempotent

Change the active project to a different codebase by name or path. This updates the token-savior MCP server context for symbol-based code navigation and editing.

Instructions

Switch the active project.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoProject name (basename of path) or full path.
pathNoAlias de `name`. Project name (basename of path) or full path.
rootNoAlias de `name`. Project name (basename of path) or full path.
projectNoAlias de `name`. Project name (basename of path) or full path.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv4.20.0
    • addedInput schema / anyOf
      Added value: +[
+  {
+    "required": [
+      "name"
+    ]
+  },
+  {
+    "required": [
+      "project"
+    ]
+  },
+  {
+    "required": [
+      "path"
+    ]
+  },
+  {
+    "required": [
+      "root"
+    ]
+  }
+]
    • addedInput schema / properties / path
      Added value: +{
+  "description": "Alias de `name`. Project name (basename of path) or full path.",
+  "type": "string"
+}
    • addedInput schema / properties / project
      Added value: +{
+  "description": "Alias de `name`. Project name (basename of path) or full path.",
+  "type": "string"
+}
    • addedInput schema / properties / root
      Added value: +{
+  "description": "Alias de `name`. Project name (basename of path) or full path.",
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "name"
-]
  2. Addedv4.0.0
  3. Removedv1.0.5
  4. Addedv1.0.4
  5. Removedv1.0.2
  6. Addedv1.0.1

TDQS

C2.6/5.0
Behavior2/5

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

Annotations already declare idempotentHint=true, destructiveHint=false, readOnlyHint=false, and openWorldHint=false, so the safety profile is covered. The description adds nothing beyond that: it does not say whether the switch persists across calls, how it affects subsequent tool calls, or what happens if the target project is unknown.

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 short, front-loaded sentence with no filler or redundancy. It is efficiently sized for the operation, though it borders on under-specification given the tool's stateful nature.

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

Completeness2/5

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

This is a stateful, session-affecting operation with no output schema and no annotations covering persistence or side effects. The description says nothing about what state actually changes, whether the effect is durable, or how failures are surfaced, leaving a significant gap for an agent that must decide when calling this is safe.

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 each of the four parameters is documented in the schema as an alias of 'name' (basename or full path). The description adds no additional meaning, so the baseline 3 applies.

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

Purpose3/5

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

It names a specific verb and resource ('switch' + 'active project'), so the surface meaning is clear. However, the sibling set_project_root plausibly performs an overlapping state change, and the description gives no basis for telling them apart, leaving the agent unable to disambiguate reliably.

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

Usage Guidelines2/5

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

There is no when-to-use, no prerequisite (e.g., project must exist or be listed via list_projects), and no mention of alternatives such as set_project_root. The agent is given no routing guidance at all.

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