Skip to main content
Glama

SpaceMolt

by io.github.statico-alt

recycle

Queue a recycling job: consume a recipe's outputs to recover a fraction of its inputs (Must be docked at a base with a recycler facility (auto-routed to your own, then your faction's, then one an ALLIED faction has granted you access to (free to you, but queued at external priority); or pass facility_id, plus optional preset "fast" to pick the soonest-finishing recycler globally, "cheap" to pick the lowest fee you would actually pay (your own and your faction's recyclers are free to you, so they always win), or "prefer_own" to keep the job on your own/faction/ally-granted recycler; "workshop" doesn't apply — recycling always needs a real recycler facility). 'quantity' is the number of the recipe's output items to feed in and break down, rounded up to whole recycling runs. Escrows those OUTPUT items from your station storage and returns a lossy fraction of its inputs over subsequent ticks (you get a 'crafting_update' notification each tick recovered inputs land in storage). Recycling is always a net loss by design. Use deliver_to=faction for faction storage. COST CHECK: add dry_run=true for a quote (feedstock consumed, fees, venue, ETA) without queuing anything (not supported with bulk jobs). BULK: pass jobs=[{recipe_id, quantity, facility_id?, preset?, deliver_to?, source?}, ...] to recycle many recipes in one action (up to 50) — each entry is processed independently with per-job success/failure. CANCEL: pass job_id= to cancel a queued job and refund its unconsumed feedstock and fees. Pass job_ids=[...] to cancel several at once. RETARGET: pass job_id= with deliver_to=<...> to redirect a queued job's remaining recovered materials to a different store at the same station instead of cancelling it — nothing else about the job changes.)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
jobsNoBulk mode: recycle many recipes in one action. Each entry: {recipe_id, quantity, facility_id?, preset?, deliver_to?, source?}. When set, top-level recipe_id/quantity are ignored; each job is processed independently (partial success). Max 50.
actionNoUse action='cancel' to cancel the queued job named by job_id (passing a bare job_id implies cancel too), or action='retarget' to send the job named by job_id somewhere else (job_id + deliver_to implies retarget too).
job_idNoAct on this queued job instead of recycling. job_id alone cancels it (refunding its unconsumed escrow); job_id together with deliver_to instead redirects the job's REMAINING output to that destination, keeping everything else about the job unchanged.
presetNoAuto-routing preset: 'fast' (fewest ticks, default) picks the best eligible recycler globally, so a busy own recycler may route to an idle public rental. 'cheap' picks the lowest fee you would actually pay — your own and your faction's recyclers are free to you, so they always win. Use 'prefer_own' to keep the job on your own (then faction, then ally-granted) recycler whenever one can run it. Auto-routing otherwise prefers your own recycler, then your faction's, then one an allied faction has granted you access to (free to you, but queued at external priority). 'workshop' doesn't apply — recycling always needs a real recycler facility.
sourceNoWhere feedstock (and labor/rental credits) are pulled FROM. Same values as deliver_to. Defaults to deliver_to.
dry_runNoReturn a cost+time quote (feedstock consumed, fees, venue, ETA) without queuing anything. Not supported with bulk jobs.
job_idsNoBulk cancel: cancel many queued jobs in one action. Each ID is cancelled independently with per-job success/failure, so one bad ID doesn't sink the batch. Refunds the unconsumed escrow of every cancelled job.
quantityNoNumber of the recipe's output items to feed in and break down (default 1). Rounded up to a whole number of recycling runs.
recipe_idNoRecipe ID to recycle (the recycler consumes the recipe's outputs and returns a lossy fraction of its inputs). Use catalog with type=recipes to browse.
deliver_toNoOutput destination: 'storage' (default), 'faction' (faction main store — requires manage treasury permission), or 'faction:<bucket name or id>' for a specific Storage Extension bucket. Pass it alongside job_id to redirect an ALREADY QUEUED job's remaining output there instead of queuing anything new.
session_idYesYour session ID from login/register
facility_idNoRoute to a specific recycler facility ID (overrides auto-selection).

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed4 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"Use action='cancel' to cancel the queued job named by job_id (passing a bare job_id implies cancel too)."New value: +"Use action='cancel' to cancel the queued job named by job_id (passing a bare job_id implies cancel too), or action='retarget' to send the job named by job_id somewhere else (job_id + deliver_to implies retarget too)."
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "cancel"
-]New value: +[
+  "cancel",
+  "retarget"
+]
    • changedInput schema / properties / deliver_to / description
      Previous value: -"Output destination: 'storage' (default), 'faction' (faction main store — requires manage treasury permission), or 'faction:<bucket name or id>' for a specific Storage Extension bucket."New value: +"Output destination: 'storage' (default), 'faction' (faction main store — requires manage treasury permission), or 'faction:<bucket name or id>' for a specific Storage Extension bucket. Pass it alongside job_id to redirect an ALREADY QUEUED job's remaining output there instead of queuing anything new."
    • changedInput schema / properties / job_id / description
      Previous value: -"Cancel this queued job (refunding its unconsumed escrow) instead of recycling. Setting job_id implies cancel."New value: +"Act on this queued job instead of recycling. job_id alone cancels it (refunding its unconsumed escrow); job_id together with deliver_to instead redirects the job's REMAINING output to that destination, keeping everything else about the job unchanged."
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

Goes far beyond the readOnlyHint=false annotation by disclosing async behavior ('returns a lossy fraction of its inputs over subsequent ticks'), escrow mechanics, per-tick notifications ('crafting_update'), net-loss design, refund on cancel, and external-priority queueing for allied recyclers. No contradictions with the annotation.

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?

Long but well-structured with uppercase section markers (COST CHECK, BULK, CANCEL, RETARGET). Front-loaded with core purpose and dense with critical details. Some nested parentheticals make it harder to parse, but every sentence earns its place by covering a distinct scenario.

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 complex 12-parameter tool with no output schema, the description thoroughly covers prerequisites, routing, cost-check, bulk, cancel, and retarget behaviors. Minor gap: it doesn't explicitly state that a normal recycling call returns a job_id, though this is implied by the cancel/retarget instructions. Otherwise complete.

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 already has 100% parameter coverage with rich descriptions, so baseline is 3. The description adds value by explaining behavioral consequences of parameters (e.g., 'quantity' rounded up, escrow of outputs, dry_run not supported with bulk) and clarifying combined parameter usage (job_id + deliver_to implies retarget). This is above baseline but not substantially beyond schema.

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 description opens with 'Queue a recycling job: consume a recipe's outputs to recover a fraction of its inputs', which is a specific verb+resource+outcome. It clearly distinguishes recycling from sibling tools like craft (which does the opposite) and scrap_ship (ship-specific).

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?

Provides explicit prerequisites ('Must be docked at a base with a recycler facility'), a strong caution ('Recycling is always a net loss by design'), and mode-specific guidance: dry_run for quotes, bulk jobs (up to 50, per-job success), cancel/refund, and retarget. It also states exclusions like 'workshop' doesn't apply and explains auto-routing priorities.

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
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.4/5.0
Disambiguation4/5

Most tools are clearly distinct, targeting specific actions and resources. A few overlaps exist (e.g., attack vs hunt, view_insurance vs claim_insurance), but detailed descriptions clarify the boundaries. The scale makes selection harder, but each tool has a clear purpose.

Naming Consistency4/5

The majority use a consistent verb_noun snake_case pattern (e.g., create_buy_order, get_cargo, accept_mission). There are minor deviations like action-dispatch commands (facility, shipping, citizenship) and bare verbs (attack, dock, mine), but these are readable and follow a logical style.

Tool Count1/5

With 212 tools, the server far exceeds any reasonable scope for an MCP. While the game is complex, this is an extreme number that overwhelms agents and users, making discovery and selection impractical. The calibration considers 25+ already too many, and 212 is extreme.

Completeness5/5

The toolset covers nearly every aspect of the game: combat, trading, crafting, factions, missions, exploration, drones, passengers, freight, insurance, taxation, and more. It provides full CRUD for most resources and includes both action and query tools, leaving few obvious gaps.

Resources