Skip to main content
Glama
Sign In

Tavern

by io.github.jakehandy
OverviewDiscussionsAdmin

Set a character's portrait

set_character_portrait
Idempotent

Wear a picture of your own, or switch back to the one from the imported sheet. Both are kept whichever is worn. Returns: The portrait choice.

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": "set_character_portrait"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoA picture's web address.
campaignYesThe campaign, by its slug (what its link says) or its id.
characterYesThe character, by its slug.
fromBeyondNoWear the imported sheet's picture instead.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world. The description adds a genuinely non-obvious behavior: 'Both are kept whichever is worn,' telling the agent that switching portraits does not discard the other asset, and it names the return value. That is real value beyond the annotations, though it omits permission/auth requirements and error behavior.

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 short sentences, purpose front-loaded, and a compact 'Returns:' note at the end. Nothing is wasted, though the opening metaphor costs a little immediate clarity that a plain verb would have avoided.

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 four-parameter tool with full schema coverage and no output schema, the description covers the core effect, the retention behavior, and the return value. Only edge cases (neither picture argument supplied, validation failures) are left to the schema or implicit.

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 the schema already explains url, campaign, character, and fromBeyond in plain terms. The description reinforces the url-vs-fromBeyond semantic split but adds no syntax, format, or precedence rules (e.g., what happens if both are supplied). Baseline 3 applies.

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?

The description conveys a specific operation on a specific resource: choosing which of two pictures a character wears. The imagery of 'wear' is a bit indirect versus a plain 'set', but the two modes (own picture vs imported-sheet picture) make the effect unambiguous and distinguish it from siblings like add_character_from_beyond or sync_character. No explicit sibling routing is given, which keeps it at 4.

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?

The two sentences implicitly define the two invocation modes: supply your own picture, or revert to the imported sheet's picture. That covers the main branching decision, but there is no statement about prerequisites (owning the character), when to choose this over related tools like sync_character, or what happens if both url and fromBeyond are omitted.

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

All Tavern toolsInspect
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.

Resources