Skip to main content
Glama
Sign In
Manthan

Manthan

by kidakaka
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

commit_memory

Validates Markdown frontmatter, atomically commits project memory to Git with agent provenance, and updates a local FTS5 index for reliable recall.

Instructions

Deterministic state write: validates Markdown frontmatter, atomically commits to Git with agent provenance, and updates local FTS5 index.

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": {
      "namespace": "<namespace>",
      "title": "<title>",
      "content": "<content>",
      "author_agent": "<author_agent>"
    },
    "name": "commit_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoTags for categorizing and discovering this memory artifact
titleYesConcise human-readable title summarizing the decision or state
contentYesMarkdown formatted memory content (facts, decisions, specs, handoff notes)
trace_idNoOptional observability trace ID correlating this memory mutation to a session/run
namespaceYesTopic namespace (e.g. "backend/payments", "architecture/auth")
author_agentYesName or identifier of the AI agent creating this memory (e.g. "claude-code", "gemini-developer")
supersedes_idNoOptional memory ID that this new artifact supersedes/replaces

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: frontmatter validation, atomicity of the Git commit, agent provenance being recorded, and a local FTS5 index update as a side effect. It omits failure modes (what happens when validation rejects), whether commits are reversible, concurrency/conflict behavior, and whether supersedes_id rewrites lineage.

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?

A single dense sentence with the core identity front-loaded and zero filler. It is slightly jargon-heavy ("FTS5", "agent provenance") but nothing is wasted.

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?

For a mutation tool with no annotations and no output schema, the description explains the write mechanics but never says what the caller gets back (a memory ID, commit SHA, or nothing) or how failures surface. Since supersedes_id implies stable memory identifiers, the missing return contract is a real gap.

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 description coverage is 100%, so every parameter including tags, trace_id, and supersedes_id is already documented in the schema. The description adds no syntax, format, or constraint detail beyond that, so the baseline of 3 applies.

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

Purpose4/5

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

"Deterministic state write" supplies a specific verb and resource, and the following clauses name the concrete mechanics (frontmatter validation, Git commit, FTS5 index update). An agent can tell this is the persistence path and not a retrieval tool like recall_memory or fetch_by_tags_and_keywords, though no sibling is named explicitly.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance, and no routing against siblings such as propose_constitution_rule or sync_memory_index. The intent to persist memory is only inferable from the word "commit".

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