Skip to main content
Glama

Cast a spell

golemreach_cast

Cast one spell. Name it by id ("light_healing") or by its incantation ("exura") — both work.

Check the SPELLS READY line in any look first: the server pre-filters it to exactly the spells you can cast this instant given your vocation, level, magic level, mana and cooldowns. If a spell is not on that line, casting it will be rejected. The full catalogue is the resource golemreach://spells.

Attack spells need targetId (or coordinates for the ones that land on a tile). Healing and support spells usually need nothing.

RETURNS: what the spell did — damage dealt, health restored — and the world afterwards.

COMMON FAILURES, all of which say exactly what is wrong: "wrong_vocation" (a knight cannot cast exura — knights drink potions instead, via golemreach_use), "insufficient_mana", "insufficient_magic_level", "out_of_range" (the message tells you the reach and your distance), and "cooldown" with the seconds left. Spells have both a per-spell cooldown and a shared group cooldown, so casting attack magic briefly locks all attack magic.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNoTarget tile x, for spells that land on a position.
yNoTarget tile y.
zNoTarget tile floor. Defaults to yours.
spellYesSpell id or incantation, e.g. "heal_light" or "exura".
targetIdNoCreature to aim at, for spells that target a creature.

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses server-side pre-filtering, rejection behavior, per-spell and shared group cooldowns, common failure codes with their meanings, and what the tool returns. This goes well beyond what the schema reveals.

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?

The description is long but dense and every section earns its place: purpose, prerequisites, target requirements, return value, and failure modes. The use of labeled sections like RETURNS and COMMON FAILURES makes the information easy to scan, and no sentences are wasted.

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?

For a five-parameter casting tool with no annotations and no output schema, the description is remarkably complete. It explains how to discover castable spells, where the full catalogue lives, how targets are chosen, what the response contains, and what errors to expect. An agent has enough context to invoke this tool correctly.

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?

The schema already describes all five parameters, so the baseline is 3, but the description adds meaningful context: spell can be supplied as id or incantation, attack spells need targetId or coordinates, and healing/support spells usually need nothing. It does not map every spell to a specific parameter combination, but it points to the catalogue for that detail.

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 states a specific action ('Cast one spell') and names the resource via 'spell id or incantation', with concrete examples like 'light_healing' and 'exura'. It clearly distinguishes spell casting from the sibling golemreach_use by noting that knights drink potions instead.

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?

The description gives explicit when-to-use guidance: check the SPELLS READY line in any look first, and only cast spells that appear there. It also names an alternative tool, golemreach_use, for knights who would otherwise try to cast healing spells, and explains when targeting parameters are required.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.8/5.0
Disambiguation5/5

Each tool maps to a clearly distinct interaction: connect, observe, move, fight, cast, use, inventory, talk, trade, knowledge/quests, wait, and admin handoff. The only possible overlap is attack versus cast, but their descriptions separate a full automated fight from casting a single spell, so an agent can reliably choose between them.

Naming Consistency5/5

All 12 tools share the golemreach_ prefix and use lowercase snake_case names in a predictable command-like style. Most are verbs (attack, move, talk, trade, use, wait), and the few non-verbs (inventory, where) still follow the same pattern, so there is no naming convention clash.

Tool Count5/5

With 12 tools, the set is well within the ideal 3-15 range for a game-agent server. Each tool earns its place by covering a distinct part of the gameplay loop—connection, exploration, combat, magic, object use, economy, NPC interaction, and progression knowledge—with no obvious redundancy.

Completeness5/5

The set covers the full lifecycle of the intended game experience: joining the world, looking and inspecting, traveling, hunting, casting spells, using items, looting, trading, talking to NPCs, tracking quests/knowledge, waiting for regeneration/cooldowns, and transferring administrative control. There are no obvious dead ends; every action a player would need flows naturally into the next tool.