Skip to main content
Glama

cleanup

Find leftover files from older Unflick versions, such as a stranded install directory, and report them; pass apply to delete them without touching live thumbnail or cover caches.

Instructions

Find files an older unflick left behind — on Windows, upgrading from v0.9 moved the install directory and stranded roughly half a gigabyte with no uninstall entry. Reports by default; pass apply to delete. The live thumbnail and cover caches share that folder and are never touched.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "cleanup"
  }
}

Input Schema

NameRequiredDescriptionDefault
applyNoDelete what was found. Omit to report only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does meaningful work: it declares the read-only default, names the single flag that makes it destructive, and explicitly bounds the blast radius by stating the live thumbnail and cover caches share the folder and are never touched. It does not cover permission requirements, irreversibility, or what happens to files that fail to delete, which keeps it out of the top band.

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?

Front-loaded with what it finds, then the motivation, then the default-vs-destructive behavior, then the exclusion boundary — a logical order with no filler. The "roughly half a gigabyte" detail earns its place by conveying scale, though it borders on narrative color for a one-parameter tool.

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 one-boolean tool with no output schema, the definition covers what is found, why it exists, the safe default, the destructive opt-in, and what is deliberately excluded. The remaining gap is post-run behavior (what a report returns, partial-deletion failures), which matters less because there is no output schema to hide behind.

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 100% and the schema already says "Delete what was found. Omit to report only." The description restates the same semantics ("pass `apply` to delete") without adding syntax, defaults, or edge-case behavior beyond it. That is the baseline for a fully documented single parameter.

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?

"Find files an older unflick left behind" gives a specific verb and a precisely scoped resource, then pins it down with a concrete example (v0.9 Windows upgrade that moved the install directory). An agent reading only this sentence knows exactly what class of files this targets, which the generic name "cleanup" would not convey.

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?

"Reports by default; pass `apply` to delete" tells the agent the default mode and the opt-in condition for the destructive path, and the v0.9 Windows detail gives a clear trigger for when this is relevant. It stops short of an explicit when-not or a named alternative, but no sibling in the catalog plausibly overlaps with stale-install cleanup, so the context is sufficient.

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

Deploy Server

Other Tools