Tavern

Change hit points, conditions or slots

update_character_state

The changes a fight makes, in one call: damage (temporary hit points go first), healing (never past the maximum), temporary hit points, conditions on and off, an exhaustion level, spell slots spent or restored, and death saves. Everything else on the sheet is left alone. Returns: What has been spent and taken, as it now stands.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "campaign": "<campaign>",
      "character": "<character>"
    },
    "name": "update_character_state"
  }
}

Input Schema

Name	Required	Description
`hp`	No	Set current hit points outright.
`heal`	No	Hit points to get back.
`damage`	No	Hit points of damage to take.
`tempHp`	No	Set temporary hit points outright.
`campaign`	Yes	The campaign, by its slug (what its link says) or its id.
`character`	Yes	The character, by its slug.
`deathSaves`	No
`exhaustion`	No	Set the exhaustion level outright, 1 to 6; 0 takes Exhaustion off. Putting it on with `addConditions` starts at 1.
`spendSlots`	No	Spell slots to spend, by level: { "1": 1 }.
`restoreSlots`	No	Spell slots to get back, by level.
`addConditions`	No	Conditions to put on.
`exhaustionChange`	No	Move the exhaustion level up (+1) or down (-1); down from 1 takes it off.
`removeConditions`	No	Conditions to take off.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations declare readOnly=false, destructive=false, and idempotent=false, so the safety profile is already covered. The description adds real behavioral semantics beyond that: damage consumes temporary hit points first, healing is capped at maximum, and the sheet outside the listed fields is untouched, which signals a partial-update model rather than a full overwrite.

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?

Two sentences with no filler, and the field enumeration is front-loaded before the scope-exclusion sentence. The opening phrasing ('The changes a fight makes') is slightly indirect where a plain verb would do, but it costs little.

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 13-parameter mutation tool with nested objects and no output schema, the description covers the important semantics and states what comes back ('what has been spent and taken, as it now stands'). The return statement is vague and there is no mention of permissions or side effects such as triggering death or unconsciousness, which is the main remaining gap.

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 already 92%, so the baseline is 3, but the description still adds meaning the schema lacks: the temp-HP-first ordering for damage and the maximum cap on healing are not stated in the corresponding property descriptions. It also flags death saves and slot spend/restore as part of the same operation, tying the nested objects together.

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 enumerates exactly which pieces of character state it mutates (damage, healing, temp HP, conditions, exhaustion, spell slots, death saves) and explicitly bounds the scope with 'Everything else on the sheet is left alone,' which separates it from siblings like update_character_draft, change_participant_health, and set_companion_state.

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

Usage Guidelines3/5

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

'In one call' implies batching multiple state changes rather than calling repeatedly, which is a genuine usage hint. However, there is no guidance on when to use this versus adjacent tools (change_participant_health, mark_character_fallen, revive_character, update_character_draft) and no stated prerequisites or exclusions beyond the scope sentence.

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

All Tavern tools Inspect

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.