Skip to main content
Glama

Edit Character

edit_character
DestructiveIdempotent

[write] Change fields of a character (same keys as create_character, among them character_note (private note, up to 500 characters, empty clears it) and character_bio; character_bio merges: only the networks sent change and an empty one clears that network, null clears the whole bio; character_name is a full name, first and last name, though an older one-word name stays valid; plus character_status: DRAFT | READY, character_main_asset_id = the MAIN-stage picture shown when the character is picked in images and videos, and character_reference_asset_id = the picture (any stage) the studio stages draw from to keep the character; empty clears either). In character_appearances, age_years is a NUMBER of years (1-110, e.g. 28), never text like "young" or "twenties"; height_cm and weight_kg are numbers too. Only the keys sent change. A character has to be READY before create_character_image, create_character_thumbnail, create_replace_image or a video can use it.

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": {
      "character_uuid": "<character_uuid>",
      "updates": "<updates>"
    },
    "name": "edit_character"
  }
}

Input Schema

NameRequiredDescriptionDefault
updatesYes
character_uuidYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description earns credit by explaining the mechanism behind both: "Only the keys sent change" (partial update / idempotency) and "empty clears it" / "null clears the whole bio" (what actually gets destroyed). It stays silent on permissions, failure behavior, or whether the response returns the updated character.

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?

Every clause carries real information with no filler, and the verb+resource is front-loaded. The cost is structure: nearly the whole definition sits inside one long parenthesis with semicolon-separated clauses, which makes the field semantics harder to scan than a short keyed list would.

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 destructive partial-update tool with no output schema and an untyped nested payload, the description covers the risky parts (merge vs. clear semantics, value formats, the READY gate for downstream tools). What is missing is modest: return value expectations and the relation to the dedicated set_* character tools.

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 0% and `updates` is a free-form object with additionalProperties=true, so the description carries the full burden — and it delivers types, the 500-character note limit, the 1-110 numeric range for age_years, the DRAFT | READY enum, and precise clearing semantics for bio and asset ids. It falls short of 5 because "same keys as create_character, among them" explicitly leaves undocumented keys for the agent to look up elsewhere, and character_uuid is unaddressed.

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?

Opens with a specific verb+resource ("Change fields of a character") and anchors the `updates` payload to create_character's key set, so an agent knows exactly what class of operation this is. It does not name the near-siblings that also mutate a character (set_character_main_asset, set_character_voice, delete_character), so differentiation is implied rather than stated.

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?

Usage is implied by "[write]" and by the READY prerequisite sentence, which tells the agent when other tools become callable, not when to pick this tool over alternatives. The overlap with set_character_main_asset (both touch the MAIN-stage picture) is never addressed, and no when-not-to-use condition is given.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.