Skip to main content
Glama
Sign In
TMF (True Memory Fragments)

TMF (True Memory Fragments)

by kyle641320
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

tmf_context

Retrieve a deterministic context bundle with code anchors and fresh graph relations when investigating a codebase, avoiding grep and whole-file reads.

Instructions

Investigating a codebase: start here; usually cheaper than grep plus whole-file reading. Return one deterministic thin context bundle with anchors and key fresh graph relations. Partial coverage; fresh != correct; source is authoritative; stale should degrade to source.

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": {
      "question": "<question>"
    },
    "name": "tmf_context"
  }
}

Input Schema

NameRequiredDescriptionDefault
questionYes
max_charsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses determinism, thinness of output, partial coverage, 'fresh != correct', source as authoritative, and graceful degradation of stale data to source. These are meaningful caveats beyond the schema, though it omits auth, rate limits, and any failure/error behavior.

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-loads the purpose ('start here') and packs caveats efficiently into a few clauses with no filler. The telegraphic, semicolon-heavy style is slightly cryptic but every clause adds signal.

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?

No output schema and no annotations exist, so the description must fully specify behavior. It covers return shape and caveats reasonably well, but leaves the two parameters undefined and gives no sense of size/scope limits despite a max_chars control, leaving notable gaps for a tool that is meant to be the first stop.

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

Parameters2/5

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

Schema description coverage is 0% for both parameters, so the description must compensate, and it does not. It never explains the 'question' format/expectations nor what 'max_chars' (minimum 180) controls or how truncation affects the returned bundle.

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?

States a clear verb and resource ('Return one deterministic thin context bundle with anchors and key fresh graph relations') and frames the tool as the entry point for codebase investigation. It distinguishes itself from the generic grep workflow, though the term 'context bundle' remains abstract and it does not name any sibling tool directly.

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

Usage Guidelines3/5

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

'Investigating a codebase: start here; usually cheaper than grep plus whole-file reading' gives a positive recommendation and a comparison to a manual alternative. However it offers no explicit when-not conditions or routing to the many siblings (tmf_retrieve, tmf_fragment, tmf_explain), so usage is only implied.

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