Skip to main content
Glama

Diastella

Project memory

project_memory
Read-onlyIdempotent

What Diastella knows about a project: its systems (the parts of the code), how many past bug reports each has and how many other systems depend on it. Start here to learn the system names the other tools take. repository is a public GitHub repository as owner/name.

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": {
      "repository": "<repository>"
    },
    "name": "project_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
repositoryYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds the shape of what comes back (systems plus two aggregate counts) and the fact that output feeds other tools, which is useful behavioral context. It says nothing about the fact that `repository` must be public (a real access constraint, only hinted at in the param sentence) or about failure behavior for private/missing repos.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the payload description, then the routing hint, then the parameter format. Every sentence contributes new information and there is no filler.

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?

With one required parameter, no output schema and a read-only annotation set, the definition covers purpose, entry-point role and parameter format, which is enough to call it correctly. The remaining gap is that the return shape (counts, dependency metric names, ordering) is only sketched rather than described, which matters slightly because there is no output schema to fall back on.

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 0% and the single parameter is only labelled 'Repository', so the description carries the burden and does so: it specifies a public GitHub repository in owner/name form. That adds format and visibility constraints the schema does not express. It omits anything about case sensitivity, URL vs slug acceptance, or what happens with private repos.

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 names the resource and enumerates its contents concretely: systems (parts of the code), past bug-report counts per system, and how many other systems depend on it. That is far more specific than the title 'Project memory' and lets an agent predict the payload. It stops short of a clean verb-first statement of what the call does, but the effect (retrieve project/system overview) is unmistakable.

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?

'Start here to learn the system names the other tools take' gives explicit sequencing guidance that no sibling name alone would convey: this is the entry point that produces identifiers used by before_you_change, check_my_change, system_history and the rest. It does not state any when-not conditions or say what to do if the project is unknown, so it is clear context without exclusions.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources