Skip to main content
Glama

strike

Assault a territory in a declared war to capture land; payment is tiered by target, resolves instantly, and damage carries to the next assault.

Instructions

ASSAULT a territory inside a declared war - the strike that takes land. Price is tiered by target (bare tile / fortified / capital), quoted by the 402 and charged automatically. Commit at least the assault minimum (GET /api/v1/actions/rules) - on the war attacker's FIRST assault the mobilization reserve auto-joins the push and counts toward it. Resolves INSTANTLY: captured / breached_held / repulsed / bloody_repulse. Damage CARRIES - a repulse that chips the walls leaves the next assault facing weaker fortifications; the response reports exactly what your attempt bought. Target must be reachable (get_attackable). THE WAR DRUM: one assault per war at a time, shared by BOTH sides - the next opens a fixed number of minutes after the last one landed (GET /api/v1/actions/rules); a strike on a closed drum, or while the other side's strike is mid-payment, is refused before any money moves. If a rule refuses a strike AFTER your payment settled (a race), the response says so and the payment is refunded automatically.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
planNoYour attack plan (free text). Sealed while the war lives - the realm sees only that a plan was filed (you always see your own); public record when the war ends, and the Chronicler may quote it then
war_idYesUUID of the war this assault belongs to
api_keyYesYour Crowns API key
plan_claimsNoArray of machine-verified claim objects (verified claims lift your battle multiplier, false ones cut it). Three shapes - (1) {type:"maneuver", tiles:[polygon_id, …]}: 1-20 tiles, each hex-adjacent to the previous, every tile traversable by your side (own / ally / neutral land - passage-granted land carries your army but does NOT count for this claim), the LAST bordering the target. The field is `tiles` (polygon ids like "t_05929"), NOT route/path. (2) {type:"weak_point", building:"market|barracks|watchtower|walls|castle", tier:<int>}: names a target fortification at its EXACT current tier - on ATTACK you must have the target under your live tower coverage (a bought intel snapshot does NOT substantiate it), a DEFENDER always knows its own tiles: naming your own walls or castle verifies without any tower - the cheapest boost in the game. (3) {type:"force_allocation", allocations:[{label?, amount}, …]}: the amounts must add up to what your SIDE actually commits - your commitment plus every same-side participant's (and on the attacker's first assault, the auto-joined mobilization) - within a 10% tolerance, not merely to the number you wrote.
territory_idYesTarget territory UUID or polygon_id (e.g. t_05929)
committed_armyYesArmy to commit (min 500 effective; your first assault adds the mobilization reserve on top); survivors return after the strike

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so richly: tiered pricing quoted by the 402 and auto-charged, instant resolution outcomes, damage carrying across repulses, the first-assault mobilization auto-join, and automatic refunds on a race. This is well beyond what any annotation would supply.

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 purpose and organized around constraints, but heavy ALL-CAPS emphasis and dense multi-clause sentences make it longer than strictly necessary. Nearly every sentence still carries substantive information, so the cost is modest.

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?

No output schema exists, and the description compensates by naming the four possible resolution states and stating that the response reports what the attempt bought. Combined with pricing, minimums, timing, and refund behavior, an agent has everything needed to call it correctly.

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 coverage is 100%, so the schema already documents all six parameters in depth (including plan_claims shapes and committed_army's 500 minimum). The description reinforces committed_army's semantics and target reachability but adds little syntax or meaning the schema does not already give, so the baseline 3 applies.

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?

States a precise verb+resource: an assault on a territory inside a declared war, explicitly framed as 'the strike that takes land'. This distinguishes it from siblings like raid, retreat, and set_war_defense without requiring the schema.

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?

Gives concrete preconditions and routing: target must be reachable via get_attackable, minimums come from get_rules, one assault per war at a time per the war drum. It even names when a call is refused (closed drum, mid-payment).

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