Skip to main content
Glama

Delete elements from a Todrawn board

board_delete
Destructive

Deletes specific elements by ID from a Todrawn whiteboard, including attached connectors, to remove requested content; the change is live and cannot be undone by this tool.

Instructions

Deletes elements by id. Connectors attached to a deleted element are deleted with it. This cannot be undone by this tool, and the person sees the change live, so delete only what was asked. Ids come from board_read.

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": {
      "boardId": "<boardId>",
      "ids": "<ids>"
    },
    "name": "board_delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsYes
boardIdYesBoard id (a UUID) from board_list or board_create.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and non-idempotency, so the safety bar is low, yet the description adds genuinely new behavior: attached connectors are deleted transitively, the deletion is irreversible through this tool, and other people on the board see it live. Cascade side effects and multi-user visibility are exactly the facts an agent cannot infer from the annotation flags.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the action and cascade consequence before the cautionary clauses; nothing is padding. It is efficiently sized for a destructive tool, though it stops just short of covering input shape.

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 destructive tool with no output schema, the definition covers consequence, irreversibility, live visibility, and id sourcing, which is close to complete. Partial-failure behavior on mixed valid/invalid ids is the main unstated case.

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 coverage is 50% — boardId is documented in-schema while ids is not — and the description only adds the provenance of those ids (board_read). It does not mention the array semantics or the 500-element cap, so it partially but not fully compensates for the uncovered parameter.

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?

"Deletes elements by id" gives a specific verb and target resource, and the cascade sentence clarifies the blast radius of that delete. It never explicitly contrasts itself with board_add or board_update, but the id-based deletion scope is unambiguous enough to select on.

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

Usage Guidelines4/5

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

It supplies both a sourcing rule ("Ids come from board_read") and a scoping constraint ("delete only what was asked"), which tells the agent how to prepare input and how conservative to be. What's missing is an explicit when-not condition, e.g. use board_update to modify instead of deleting and re-adding.

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