Skip to main content
Glama

mv_load_scars

Load weighted corrective lessons from past contradictions to ground reasoning in audit lenses, sharpening insights into what consensus might suppress.

Instructions

Load the system's accumulated scars (corrective lessons), weighted by recency × reinforcement.

Use this in audit lenses to ground reasoning in what the system has been re-taught. Most useful for the Diverger lens: "what would consensus kill?" sharpens significantly when read against the system's own history of contradictions.

Weighting formula: weight = exp(-ageDays/30) × (1 + log2(1 + reinforceCount))

  • 30-day recency halflife.

  • Logarithmic dampening on reinforcement (1 = ×2, 3 = ×3, 7 = ×4).

  • A scar reinforced 3+ times from 30+ days ago beats a one-time recent correction.

Scar source: feedback_*.md files in the memory directory. Each file's frontmatter:

name: description: type: feedback reinforces: # optional; absent = independent date: # optional; absent = falls back to file mtime

Default directory: ${HOME}/.claude/projects/${encoded-cwd}/memory Override via SCAR_DIR env var or scar_dir param.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
top_nNoLimit to top N scars by weight. Omit for all.
include_bodyNoInclude full prose body of each scar. Default false (header + description only).
filter_typeNoFilter by frontmatter `type:` field. Default "feedback". Use "all" to disable.
scar_dirNoOverride the scar directory. Falls back to SCAR_DIR env var, then computed default.
Behavior4/5

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

No annotations, so description bears full burden. Details weighting formula, file format, default directory, and env var override. Does not mention auth or side effects, but tool appears read-only and safe.

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?

Well-structured with purpose first, then usage, formula, file format, and defaults. A bit lengthy but each section earns its place. Could be slightly more terse.

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

Completeness3/5

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

Covers usage, weighting, file format, and parameters thoroughly. However, lacks description of the output format (what the loaded scars look like). Tool is complex; output structure is important for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, adding baseline of 3. Description adds significant value: explains top_n limiting, include_body default, filter_type options, and scar_dir override chain. Also describes weighting formula and file frontmatter beyond schema.

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 clearly states 'Load the system's accumulated scars' with specific verb and resource. It explains the weighting by recency × reinforcement, and the tool is distinct from all DeFi 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?

Specifies use in audit lenses, especially the Diverger lens. Provides concrete usage context but does not explicitly exclude alternative tools or state when not to use.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Finanzgoblin/spectra-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server