Skip to main content
Glama

update_object

Modify fields of a Wonderdraft map object by ID, including rotation, scale, sprite, texture, style, position, colors, and points, with type-checked values.

Instructions

Update fields of one object (id like "label:3", see list_objects). Values are checked against the type Wonderdraft stores for each key; unknown keys are rejected with the valid list.

  • rotation: degrees, clockwise, for symbols and labels alike (symbols are stored in radians).

  • scale (symbols): a number or [x, y], a multiplier on the set's base size, the same meaning as add_symbol's scale (list_objects shows the current multiplier).

  • variant (symbols): sprite index within the symbol's set (or within the set given as texture in the same call); texture: a sprite path. Packs are registered as needed.

  • style (paths/territories): a path or border texture name as in add_path / add_territory.

  • Vectors (position, offset) are [x, y]; colours are [r, g, b(, a)] floats 0-1 or "#rrggbb"; points (path/territory) are [[x, y], ...].

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": {
      "id": "<id>",
      "fields": "<fields>"
    },
    "name": "update_object"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
fieldsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

No annotations exist, so the description carries the full behavioral burden. It does disclose valuable traits: values are validated against Wonderdraft's stored types, unknown keys are rejected with the valid key list, symbols are stored in radians despite degree input, and asset packs are registered as a side effect. It says nothing about permissions, whether unspecified fields are preserved, or effects on other objects.

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?

Front-loaded with the core action and ID convention, then organized into tight per-key bullets. Dense but every line conveys non-obvious type or unit information; nothing is redundant.

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 two-parameter mutation tool with no output schema, the description covers identity, accepted field vocabulary, value validation, and error behavior. Remaining gaps are whether fields not listed are left untouched and whether the result can be verified (there is a list_objects sibling, but no mention).

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?

Schema coverage is 0%, yet the description compensates thoroughly: id format is exemplified, and the free-form fields key space is documented per type with units and encodings (degrees vs radians, scale as number or [x,y], variant/texture, style names, [x,y] vectors, [r,g,b(,a)] floats or hex, points as arrays). It even notes rejection behavior for unrecognized keys, covering the open-ended additionalProperties object.

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?

States a specific verb and resource ("Update fields of one object") and gives the ID format with a pointer to list_objects, so the agent knows exactly what is being mutated. It implicitly contrasts with creation tools by borrowing add_symbol's scale semantics and add_path/add_territory's texture naming, but never states the create-vs-modify boundary outright.

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 context is implied: fetch an id via list_objects, then update fields. There is no explicit when-to-use/when-not guidance and no routing to siblings like move_objects or remove_objects for related operations. The references to add_symbol/add_path are about field value formats, not about choosing between tools.

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