Skip to main content
Glama

get_project_knowledge

Read-onlyIdempotent

Extract the permanent knowledge base of a project. Access accumulated context, recorded decisions, and workspace memories to build a complete historical picture.

Instructions

Get the PERMANENT KNOWLEDGE of a project: decisions, conventions, accumulated context. Returns workspace-level + project-level memories (workspace tier paged by limit/offset and narrowed by min_importance and tags_any). Use it for the standing picture of ONE project; get_context returns what happened recently, recall searches all memory for one specific fact, get_canonical returns owner-curated decisions on a topic.

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": {
      "project_id": "<project_id>"
    },
    "name": "get_project_knowledge"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax workspace-tier memories (default 100, max 500).
offsetNoPagination offset for workspace-tier (default 0).
tags_anyNoComma-separated tag OR-filter for workspace-tier, e.g. 'kind:decision,kind:incident'.
project_idYesUUID of the project whose knowledge to load (list_projects returns ids).
min_importanceNoMinimum importance_score for workspace-tier (default 0 = all).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.6
    • changedInput schema / properties / project_id / description
      Previous value: -"Project UUID."New value: +"UUID of the project whose knowledge to load (list_projects returns ids)."
  2. First observedv0.1.1

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds behavior the annotations don't: the two-tier return structure (workspace + project), that only the workspace tier is paged and narrowed, and that the tool returns 'permanent' rather than recency-ordered content.

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?

Three sentences, front-loaded with the core purpose and the routing guidance. The parenthetical on paging is dense but every clause carries information; minor cost is readability of the nested filter detail.

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?

A read-only retrieval tool with full schema coverage and no output schema; the description covers scope, tiering, filtering, and alternatives. It stops short of describing the shape of a returned memory (fields, ordering), which would be the remaining gap for an agent planning a call.

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%, so baseline is 3. The description adds the key semantic that limit/offset/min_importance/tags_any apply only to the workspace tier, implying project-tier memories are returned in full and unfiltered—a distinction the per-parameter descriptions state individually but not as a whole-tool rule.

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?

States a specific verb and resource ('Get the PERMANENT KNOWLEDGE of a project') plus the content types it covers (decisions, conventions, accumulated context) and the two-tier scope (workspace-level + project-level). An agent can distinguish this from get_context, recall, and get_canonical without opening any schema.

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

Usage Guidelines5/5

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

Explicitly names the three nearest alternatives and the condition that selects each: get_context for recent activity, recall for one specific fact, get_canonical for owner-curated decisions on a topic. It also states the positive selector ('standing picture of ONE project'), leaving nothing to inference.

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