Tavern

Edit a companion

update_companion

DestructiveIdempotent

Replace a companion's stat block. Returns: The companion.

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>",
      "companion": "<companion>"
    },
    "name": "update_companion"
  }
}

Input Schema

Name	Required	Description
`ac`	No	Armor class.
`kind`	No	What creature it is, in your words.
`name`	No	Its name. Required.
`type`	No	What kind of companion.
`boxes`	No	Its actions and traits.
`hpMax`	No	Maximum hit points.
`notes`	No	Free notes.
`saves`	No	Saving throw bonuses.
`speed`	No	Speed line.
`scores`	No	The six scores.
`senses`	No	Senses line.
`skills`	No	Skills line.
`campaign`	Yes	The campaign, by its slug (what its link says) or its id.
`imageUrl`	No	A picture's web address.
`sizeLine`	No	Size and type line.
`character`	Yes	The character, by its slug.
`companion`	Yes	The companion's id.
`hpFormula`	No	How the hit points are rolled.
`languages`	No	Languages line.
`initiative`	No	Initiative bonus.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description reinforces this with "Replace" and adds the return value, but it never clarifies the most important behavioral question for a 20-parameter tool: whether replacement means omitted fields are cleared or preserved. That ambiguity is exactly what an agent needs spelled out for a destructive edit.

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?

Two short sentences, front-loaded with the action and followed by the return value. With no output schema, the return note is functional rather than filler, and there is no wasted wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, 20-parameter tool with nested objects and no output schema, the description is too thin: it omits replacement-vs-merge semantics, whether the companion must exist, and any note about the shape of the returned companion. The rich schema covers field formats, but it cannot resolve the core mutation semantics, leaving a significant gap.

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 description coverage is 100%, so every parameter including nested box, attack, save, and uses fields is documented in the schema itself. The description adds no parameter-level meaning, which is acceptable at full coverage but earns only the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Replace a companion's stat block" gives a specific verb (replace) and resource (companion stat block), and the word "replace" usefully distinguishes this from add_companion. It stops short of naming the sibling tools (add_companion, set_companion_state) it must be distinguished from.

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

Usage Guidelines2/5

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

There is no explicit when-to-use guidance, no statement of prerequisites (e.g., the companion must already exist), and no routing to alternatives such as add_companion for creation or set_companion_state for runtime state. The only implied guidance is that this is for existing companions, derived entirely from the verb "replace".

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.