Skip to main content
Glama

OpenAkashic

by io.github.szara7678

Self-test Your OpenAkashic Usage Skill

run_self_test

Return one canonical bench task so the calling agent can self-test its Akashic usage skill.

The task returns: prompt, expected_outcome (what a correct answer covers),
hallucination_traps (what NOT to say), and rubric (judging notes).

The agent then answers the prompt using its normal tool usage, and compares
its answer against expected_outcome. This is self-assessment — no server-side
judgment happens here. The judge script at closed-web/server/bench/judge.py
can be run manually by an admin to score actual responses.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
task_idYesTask ID from OpenAkashicBench public subset. Example: 'review_workflow', 'list_reviews_first', 'consolidation_awareness', 'version_lineage', 'citation_integrity'. Full list: run_self_test(task_id='list_tasks').

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and meets it. It explicitly states the tool returns a task with prompt, expected_outcome, hallucination_traps, and rubric, and clarifies that this is self-assessment with 'no server-side judgment happens here.' It also mentions the judge script for admin use, disclosing the full behavioral context. This goes beyond simple retrieval and manages expectations about what the tool does not do (e.g., score responses).

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?

The description is front-loaded with the core purpose, followed by a concise breakdown of the return structure and usage process. Every sentence earns its place: it explains what is returned, how to use it, and the self-assessment nature. It is neither overly terse nor bloated, and it is well-structured for quick comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (single param, read-only retrieval) and the presence of an output schema, the description fully covers the necessary context. It explains the return fields and the self-assessment workflow, including the caveat about no server-side judgment and the existence of an admin judge script. There are no significant gaps for an agent to misunderstand the tool's function.

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?

The input schema already provides 100% coverage for the single parameter task_id, including concrete examples ('review_workflow', 'list_reviews_first', etc.) and instructions for listing all tasks (run_self_test(task_id='list_tasks')). The description itself adds no additional parameter information, but the schema is already rich. Per the calibration baseline, a score of 3 is appropriate when schema carries the load.

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?

The description opens with a specific verb+resource: 'Return one canonical bench task so the calling agent can self-test its Akashic usage skill.' This clearly distinguishes it from sibling tools, which are all operational tools for note management and search. The purpose is unambiguous and immediately understandable.

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?

The description clearly frames the intended use: the agent calls this tool to get a task for self-assessment, then answers the prompt using normal tool usage and compares against expected_outcome. This provides clear context and a step-by-step workflow. However, it does not explicitly state when not to use the tool or name alternatives, but no sibling offers similar functionality, so the absence is not a major gap.

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

All OpenAkashic toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.5/5.0
Disambiguation4/5

Most tools have clear, distinct purposes, but there are overlapping areas such as search_akashic vs search_notes vs search_and_read_top, and confirm_note/dispute_note/review_note which serve related but different review functions. Descriptions are detailed enough to reduce ambiguity, though some boundary cases require careful reading.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern (e.g., list_notes, create_folder, delete_note, move_note). Even debug tools and compound names like search_and_read_top maintain the convention. The only exception is whoami, which is a common standalone verb and does not break the overall pattern.

Tool Count2/5

With 35 tools, the server has a large surface area that could overwhelm agents. The tool count exceeds the 25+ threshold for 'too many' in the rubric, even though the broad domain (notes, folders, search, reviews, publication workflow, debugging) partially justifies the number. The set feels heavy and could benefit from consolidation.

Completeness5/5

The toolset provides thorough coverage of the knowledge management lifecycle: note CRUD (upsert/read/delete/move), folder management, multiple search modes, review/confirmation/dispute mechanisms, publication workflow, stale note handling, image upload, and debugging utilities. There are no obvious dead ends; every major operation needed to manage and publish notes is represented.

Resources