Skip to main content
Glama
ty-meador

civ-v-llm-harness

by ty-meador
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

inspect

Read-onlyIdempotent

Read-only view of the game your seat sees—units, cities, map, options—returning copy-ready action rows for orders; verify state before and after moves, even off-turn.

Instructions

Read the game as my seat sees it: the empire, units, cities, civs and city-states, the map, the league, spies, the screens, and the choices open to me (research, policies, beliefs, trade routes). Read-only, no side effect, usable while it is not my turn. Use it before an order (its rows ARE the orders) and after one to verify; use reference for what things do, question for what a popup asks, turn for the turn's own state. How to call: what names the object, view the part of it (left out: the default view), id the one object. Objects and their views: empire: default, demographics notifications: default screen: tech_tree, religion, culture, culture_works, great_people, domination, spaceship, wonders, intrigue, trade_routes, deals league: default spies: default units: default, actions unit: actions, targets, tactical, home cities: default city: screen, production, strikes map: window, grid, index, frontier civs: default civ: summary, war, trade_catalog city_state: summary, full options: research, policies, beliefs, trade_routes, spy_cities compare: default Selectors, by view: x, y, radius for map/window and unit/tactical; mission for unit/targets; kind for options/beliefs and compare; detail ('summary' / 'full') where a view has both; since and limit for lists; item and yield_type for city/production to price one item; args for the rest by the old call's name. Returns: the object as JSON (a list for units, cities, civs; one dict otherwise), with actions or call rows wherever something can be done: each row is a complete order() call to copy. A wrong what or view is refused with choices, and for an object that takes an id, a hint saying where the ids come from (unit ids from units, city-state ids from the minor: true rows of civs). Replies are the 1.x reads' replies unchanged.

Input Schema

NameRequiredDescriptionDefault
xNomap/window centre or unit/tactical origin, with y
yNowith x
idNothe one object's id (unit, city, civ, city-state or spy); a list of unit ids for units/actions
argsNothe rest by the old call's name (compare's fields)
itemNocity/production: price this one item
kindNooptions/beliefs: the belief kind; compare: what to compare
viewNothe part of the object, from the list below; the default view when left out
whatYesthe object: empire, notifications, screen, league, spies, units, unit, cities, city, map, civs, civ, city_state, options, compare
limitNohow many rows a list returns
sinceNonotifications: only those after this turn
detailNo'summary' or 'full' where a view offers both
radiusNomap/window, unit/tactical: tiles around x, y
missionNounit/targets: the mission whose legal targets to list
yield_typeNocity/production with item: the yield to price it in

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent safety; the description adds real behavioral context beyond them — out-of-turn usability, refusal behavior for bad `what`/`view` (returns `choices`, and a `hint` for id-taking objects with the id provenance explained), and the action-row format. That is materially more than the annotations convey.

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?

Purpose is front-loaded, then call convention, then return shape — a sensible order with almost no filler. The dense objects/views block is long but each line carries distinct lookup value; only the closing migration note ("the 1.x reads' replies unchanged") is low-value to a new caller.

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 14-parameter, no-output-schema dispatcher, the description supplies the missing view taxonomy, selector applicability, error semantics, and return shape. An agent can construct a valid call from this alone without trial and error.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema's `view` field points to "the list below" which only exists in the description, so the object→view enumeration is load-bearing documentation. It also maps selectors to views (x/y/radius for map & tactical, mission for targets, item/yield_type for production pricing) and explains the `id` provenance, far beyond the flat schema strings.

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?

"Read the game as my seat sees it" gives a concrete verb and resource, then enumerates the exact object families it covers (empire, units, cities, civs, map, league, spies, screens, options). It explicitly differentiates from siblings: "use reference for what things do, question for what a popup asks, turn for the turn's own state."

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?

States both when to use ("before an order... and after one to verify") and when to route elsewhere (reference / question / turn), plus a non-obvious availability rule: "usable while it is not my turn." Nothing about tool selection is left to inference.

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