Skip to main content
Glama

project_context

DestructiveIdempotent

Load and update persistent per-project markdown context stored on the MCP server, so each AI session reuses known architecture, conventions, and gotchas instead of re-exploring.

Instructions

Persistent per-project AI context (markdown) stored on the MCP server at ~/.tufan-blox-bridge/context/.md — survives sessions and is shared by every AI session that touches this place. CALL get AT SESSION START, BEFORE exploring the place: it carries hard-won facts (architecture, conventions, gotchas, false-bug-report traps) that save tokens and prevent wrong conclusions. set overwrites the blob; append adds a dated entry — update it whenever you learn something durable about the place (a confirmed bug's root cause, a naming convention, a do-not-touch area). get works in read-only mode; set/append are write-gated. An explicit numeric PlaceId works even with no Studio connected (storage is local).

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": {
      "action": "<action>"
    },
    "name": "project_context"
  }
}

Input Schema

NameRequiredDescriptionDefault
placeNoTarget place (PlaceId or project name). Defaults to the bound/sole connected place.
actionYesget = read the blob; set = overwrite it (needs content); append = add a dated entry (needs content)
contentNomarkdown content (required for set/append). Total stored size is capped at 64 KB.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the annotations, it discloses the storage location, cross-session and cross-AI-session persistence, that set overwrites the whole blob (consistent with destructiveHint=true), that get is read-only while set/append are write-gated, and that a numeric PlaceId works with no Studio connected. One tension is left unaddressed: append adds a new dated entry per call, which sits awkwardly with idempotentHint=true, and the description does not reconcile that.

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 paragraph is front-loaded with what the tool is before moving to when to call it, and every clause carries information. It is dense but readable. Minor waste comes from re-explaining set/append and the 64 KB cap that the schema already states.

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?

Three parameters, no output schema, and populated annotations mean the description only needs to cover persistence, write gating, overwrite consequences, and timing, all of which it does. It leaves a small gap around what get returns when no context file yet exists for a place, which an agent might reasonably wonder before calling it at session start.

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%, so the schema already documents place, action, and content, giving a baseline of 3. The description adds one genuinely new fact beyond the schema: an explicit numeric PlaceId works even when no Studio is connected because storage is local. It otherwise restates the action semantics the enum descriptions already carry, and the 64 KB cap duplicates the schema.

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?

The description states a concrete verb+resource: persistent per-project AI context stored as markdown at a specific server path, with the three actions (get/set/append) spelled out. It is immediately clear what the tool manipulates. It does not explicitly differentiate itself from the similarly named sibling project_health, which is the only thing keeping it from a 5.

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?

Usage timing is unusually explicit: call get at session start, before exploring the place, and update via set/append whenever a durable fact is learned (root cause, naming convention, do-not-touch area). Concrete examples of what belongs in the blob make the trigger conditions unambiguous. There is no explicit when-not guidance or named alternative, so it falls short of a 5.

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