Achriom

Query my library

query

Read-onlyIdempotent

Read anything in the user's own Achriom data with one SQL SELECT over the me.* views. me.items has every title of every kind: kind, id, title, creator, year, status, rating (stars 0.5-5), notes, priority, started, finished, added, genres. me.books/movies/albums/shows/anime/podcasts/games/manga have the same columns plus that kind's own (page_count, runtime_minutes, platform, hours_played, episodes_watched...). Also me.events (history: kind, item_id, event_type, event_date, rating), me.show_episodes, me.lists, me.list_items, me.reviews, me.hidden, me.page, me.pins, me.nines, me.favorites_on_page, me.challenges, me.challenge_slots (each prompt, its pick, and read_on: the day it was read inside the challenge's dates). Read-only, their rows only, up to 200 rows, 3 seconds. describe lists every column. Prefer this for any question about their library ("albums I rated 4+ but never finished", "what I finished each month this year").

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": {
      "sql": "<sql>"
    },
    "name": "query"
  }
}

Input Schema

Name	Required	Description	Default
`sql`	Yes	One SELECT (WITH is fine). Example: SELECT kind, title, rating FROM me.items WHERE rating >= 4.5 ORDER BY finished DESC LIMIT 20

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 4, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing hard operational limits (up to 200 rows, 3 seconds), the row-level security scope ('their rows only'), and the read-only guarantee at the query level. These are exactly the constraints an agent needs to shape a query that will not fail.

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-loaded with the core mechanism, then constraints, then the routing recommendation — the right order. The dense view/column enumeration is long but functional; a small amount of the column listing (page_count, hours_played, episodes_watched...) could be compressed without losing guidance.

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?

No output schema exists, yet the description effectively defines the return shape by enumerating the available views and columns, and it supplies the limits and safety constraints. Nothing an agent needs in order to write a valid, in-scope query is missing.

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

Parameters5/5

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

Schema coverage is 100%, but the description adds substantial meaning the schema cannot: the full set of queryable views and their columns (kind, id, title, creator, year, status, rating scale 0.5-5, notes, priority, dates, genres), kind-specific extras, and the event/challenge semantics. That vocabulary is what actually determines a correct SQL string.

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 mechanism ('Read anything in the user's own Achriom data with one SQL SELECT over the me.* views') plus the exact surface queried. The named view catalog (me.items, me.books, me.events, me.challenges, ...) makes it unmistakable versus siblings like search_library or get_by_rating.

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?

Explicitly routes the agent here ('Prefer this for any question about their library') with two concrete example questions, and points to the describe sibling for the full column list. It does not say when to prefer a narrower sibling such as search_library or get_by_rating instead, so it stops short of full when/when-not guidance.

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

All Achriom tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?