Skip to main content
Glama
DanceNitra

inspeximus

by DanceNitra
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

erasure_residue

Scan directories to verify erased data is truly gone, distinguishing live rows, unreclaimed storage, and plain-text residues. Returns fingerprint-based findings without exposing values.

Instructions

DID THE BYTES ACTUALLY GO? (read-only, no LLM) Scan a directory for values that should have been erased — ANY store, not just this one: a vector database, a sqlite history, a JSONL trace, another library's data dir. delete() returning success is not the same as the value being gone from disk.

Separates three outcomes, and the distinction is the point: LIVE (a table still holds it in a row — the system retained it), UNRECLAIMED (in the bytes but in no row — the storage engine has not reclaimed the page; run VACUUM/compact, and do NOT report this as a vendor defect), PLAIN (a JSON, log or backup still has it; nothing reclaims that on its own).

Never echoes the values you pass — findings carry a 12-char fingerprint, because a tool that hunts a secret and then prints it into a transcript is itself the leak. A file it could not read, a directory it could not list, or a symlinked directory it did not enter makes the verdict False and is named in skipped: "clean" must never mean "we did not look at that part".

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rootYes
valuesYes
max_file_mbNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.20.1

TDQS

A4.3/5.0
Behavior5/5

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

With no annotations, the description bears full responsibility and delivers: it declares read-only behavior, no LLM involvement, non-echoing of secrets via 12-char fingerprints, and precise failure semantics where unreadable files/unlisted directories/symlinks force a False verdict and appear in skipped. It also names concrete storage contexts and remediation actions.

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?

The description is longer than average, but it is organized into purpose, outcome taxonomy, and safety/failure behavior with no filler. The all-caps hook adds tone without substantive cost.

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?

The tool is complex, has no output schema, and no annotations, so the description must carry a lot; it covers what kinds of stores are scanned, what each outcome means, how findings are fingerprinted, and how skips affect the verdict. The main gap is the undocumented max_file_mb parameter and the precise shape of the returned verdict/status fields.

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 0%, so the description must illuminate the parameters. It indirectly clarifies 'root' as the directory to scan and 'values' as the secrets or values to search for, but 'max_file_mb' is never explained, including what happens to skipped oversized files.

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?

The description specifies a concrete operation: scanning a directory for residue of values that should have been erased, and explicitly frames it as verifying physical erasure across any store. The three outcome categories (LIVE, UNRECLAIMED, PLAIN) distinguish it from likely report/audit siblings.

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 gives clear usage context: use when a logical delete succeeded but you need to verify the bytes are really gone, and use across arbitrary stores, not only this system. It also advises interpreting UNRECLAIMED as a storage-engine reclamation issue rather than a vendor defect, but it does not explicitly contrast itself with sibling tools like erasure_report or verify_writes.

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