Skip to main content
Glama
bunkerity

BunkerWeb MCP

Official

cache_delete_bulk

Destructive

Deletes multiple job cache files by queueing the request for the scheduler. Use for bulk cleanup; single file deletion uses a separate tool.

Instructions

Delete several job cache files. Use cache_delete_file for one; jobs_run regenerates them. Queued for the scheduler; this tool cannot confirm it ran.

Input Schema

NameRequiredDescriptionDefault
filesYesCache files to delete, each keyed as in cache_list

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.6.0
    • addedInput schema / $defs / CacheFileKeyParams / properties / file_name / description
      Added value: +"File name, as listed by cache_list"
    • addedInput schema / $defs / CacheFileKeyParams / properties / job_name / description
      Added value: +"Job that wrote the file, as listed by cache_list"
    • addedInput schema / $defs / CacheFileKeyParams / properties / plugin / description
      Added value: +"Plugin ID that owns the file, as listed by cache_list"
    • addedInput schema / $defs / CacheFileKeyParams / properties / service / description
      Added value: +"Service ID that owns the file; omit for global"
    • addedInput schema / properties / files / description
      Added value: +"Cache files to delete, each keyed as in cache_list"
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

The destructiveHint annotation already declares the safety profile, yet the description adds two facts the annotations cannot: the work is queued for the scheduler and the tool cannot confirm execution. That async, fire-and-forget trait is critical for a destructive op. It stops short of stating permission prerequisites or whether a delete can be undone, keeping it below a 5.

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?

Three short sentences, zero padding, with the action front-loaded and the caveat and alternative packed into the remainder. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, asynchronous bulk tool with fully described parameters and no output schema, the description covers the action, the sibling alternative, the regeneration path, and the inability to confirm success. Nothing an agent needs to call it correctly is missing.

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?

The single top-level parameter is fully documented in the schema (coverage 100%), including nested keys cross-referenced to cache_list. The description adds no syntax or format detail beyond that, so the schema carries the load and baseline 3 applies.

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 with explicit cardinality: 'Delete several job cache files.' It immediately distinguishes itself from the singular sibling by naming cache_delete_file, so an agent can pick between them without opening either schema.

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?

Explicitly routes single-file deletion to cache_delete_file and explains the recovery path ('jobs_run regenerates them'), which is exactly the context needed before invoking a destructive bulk operation. No ambiguity about when this tool versus its alternative applies.

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