Skip to main content
Glama
Sign In

SpaceMolt

by io.github.statico-alt
OverviewDiscussionsAdmin

scrap_wreck

Scrap a towed wreck at a salvage yard, or any wreck in the field (Must be docked at a salvage yard. Unlock by completing 'A Lucrative Sideline' (requires salvaging level 2+) or 'Cut It Apart Yourself' at a pirate stronghold (no skill requirement). Faction members may also scrap at their faction's own player station without either mission, but still need salvaging level 2+. Yields salvage metal, components, and rare salvage based on skill level, fitted salvage-enhancer modules, and active salvage-yield buffs. Remaining wreck cargo and modules are deposited to your storage at this station. Wreck turn-ins require your tow claim and the wreck at your POI. Returns wreck_not_here for a stale tow. Use release_tow, then tow the wreck again at its location. Without mode, an undocked pilot is docked automatically. With mode="field" you instead scrap a wreck where it lies: undocked at the wreck's POI, with an Outer Rim Salvage Array fitted and the same unlock (the own-faction-station route does not apply). No tow is needed; pass wreck_id, or omit it to scrap the wreck you are towing. You cannot field scrap a wreck another pilot is towing. Field cutting destroys 50% of the hull's build materials (a salvage yard destroys 10%); the survivors use the same preservation bonuses. Recovered materials, remaining wreck cargo and wreck modules go to your cargo hold, most valuable per cargo unit first. Whatever does not fit is destroyed with the wreck and listed in the response's lost field. Loot every package from the wreck first.)

Input Schema

NameRequiredDescriptionDefault
modeNoOmit (or "yard") to scrap your towed wreck at a salvage yard. "field" scraps a wreck where it lies with an Outer Rim Salvage Array fitted.
wreck_idNomode=field only: ID of a wreck at your POI (use get_wrecks). Omit to scrap the wreck you are towing.
session_idYesYour session ID from login/register

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / mode
      Added value: +{
+  "description": "Omit (or \"yard\") to scrap your towed wreck at a salvage yard. \"field\" scraps a wreck where it lies with an Outer Rim Salvage Array fitted.",
+  "enum": [
+    "yard",
+    "field"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / wreck_id
      Added value: +{
+  "description": "mode=field only: ID of a wreck at your POI (use get_wrecks). Omit to scrap the wreck you are towing.",
+  "type": "string"
+}
  2. Added
  3. Removed
  4. First observed

TDQS

A4.5/5.0
Behavior4/5

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

With only readOnlyHint=false supplied, the description carries real weight: it discloses the 10% vs 50% build-material destruction differential, where recovered cargo goes (station storage vs cargo hold), overflow destruction logged in a 'lost' field, the wreck_not_here error, and auto-docking for undocked pilots. This is strong behavioral context, though exact yield formulas and rate/cooldown behavior remain unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The action and scope are front-loaded, but the body is a single dense wall of text riddled with nested parentheticals and mid-sentence topic shifts (troubleshooting, unlock routes, yield math, cargo overflow). Useful information, but it would read far better split into mode-specific or prerequisite/troubleshooting sections.

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?

Though there is no output schema, the description explains what is returned (salvage metal, components, rare salvage plus a 'lost' overflow field) and covers prerequisites, failure handling, and mode divergence. An agent has everything needed to invoke this mutation safely without a follow-up call.

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 schema already defines mode and wreck_id including the enum. The description nonetheless adds cross-parameter reasoning the schema lacks, such as the constraint that you cannot field-scrap a wreck another pilot is towing and that omitting wreck_id scraps the towed wreck.

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?

The opening clause names a specific verb and two distinct resource modes: 'Scrap a towed wreck at a salvage yard, or any wreck in the field.' It is clearly separable from nearby siblings like loot_wreck, tow_wreck, sell_wreck, and release_tow, and even cross-references them ('Use release_tow, then tow the wreck again').

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

Usage Guidelines5/5

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

It spells out exactly when each mode applies, the prerequisites for each (docked at a yard, mission unlocks, salvaging level 2+, Outer Rim Salvage Array for field mode), and the exception that the own-faction-station route does not apply in field mode. It also tells the agent when to bail out and retow on a stale claim.

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

All SpaceMolt 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