Skip to main content
Glama

Delete one block

delete_block
Destructive

Permanently delete one block and all links touching it to clean up orphaned or superseded content, leaving the rest of the workspace intact. Omit confirm to preview; set confirm=true to execute.

Instructions

Permanently deletes ONE block and every link touching it, leaving the rest of the workspace alone — use it to clean up orphaned or superseded blocks. Requires confirm=true; call without confirm first to preview. A deployed endpoint bound to this block is NOT removed (delete it with delete_endpoint), and an on-prem runner behind a SignalR block is left provisioned.

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": {
      "workspaceId": "<workspaceId>",
      "blockId": "<blockId>"
    },
    "name": "delete_block"
  }
}

Input Schema

NameRequiredDescriptionDefault
blockIdYes
confirmNoMust be true to delete. Omit/false returns a preview only.
workspaceIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.53.0

TDQS

A4.5/5.0
Behavior5/5

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

The destructiveHint annotation only says the tool is destructive; the description adds what actually gets destroyed (the block plus every touching link), what is explicitly NOT destroyed (deployed endpoint, on-prem runner behind a SignalR block), and a reversible preview path via confirm omission. That is substantive behavior beyond the annotation.

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 sentences, front-loaded with the core effect and cascade scope before the caveats. Every clause carries information, though the second sentence stacks three distinct exceptions (confirm flow, endpoint, runner) and would be marginally scannable as a short list.

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 3-parameter tool with no output schema, it covers cascade effects, non-effects, and the confirm gate, which is what an agent most needs to avoid a bad call. It stops short of stating failure behavior (nonexistent block, insufficient permission) or what the preview response contains.

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?

With schema coverage at 33%, only confirm is documented in the schema, and the description reinforces it with the preview-then-confirm workflow, which is useful. However, workspaceId and blockId get no semantic treatment at all — no note on cross-workspace behavior, blockId provenance, or errors for unknown IDs — so half the gap is left unclosed.

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

Purpose5/5

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

States a specific verb and resource ('Permanently deletes ONE block') plus the blast radius ('every link touching it, leaving the rest of the workspace alone'). The capitalized ONE sharply scopes it apart from bulk delete siblings, and it names delete_endpoint as the tool for the related object.

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

Usage Guidelines5/5

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

Gives an explicit use case ('clean up orphaned or superseded blocks'), a required invocation workflow (call without confirm first to preview), and an explicit carve-out routing the agent to delete_endpoint for bound endpoints. The only remaining case it doesn't route is blocks that are still referenced, which is implied by 'orphaned or superseded'.

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