mcp-server

Hands Facts

alterlab_facts

Evidence-backed fact store for the signed-in user (and organisation). action=get returns the latest version of facts (pass subject and key for one, or subject/prefix to list); action=history returns every version of one subject+key; action=put records a user assertion, which is unconfirmed until the user confirms it; action=confirm adds the confirmed version after the user said it is right. Facts are insert-only: a put adds a new version. Only a connector or the platform's own tools produce verified facts; a put never does. Every fact lists its sources with step_id, job_id, url, fetched_at, tier and evidence.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "alterlab_facts"
  }
}

Input Schema

Name	Required	Description
`key`	No	Namespaced key, e.g. user.address.home
`kind`	No	Value type slug, e.g. address, money, text
`as_of`	No
`limit`	No
`ttl_s`	No	Seconds the fact stays fresh
`value`	No	The fact value (put)
`action`	No	Default get
`prefix`	No	List facts whose key starts with this (get)
`subject`	No	Whose fact, e.g. user or org.acme
`version`	No	A specific version (get)
`confidence`	No
`system_of_record`	No	Where the fact lives

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description discloses key behavior: insert-only versioning, that a put never yields a verified fact, and that only connectors/platform tools produce verified facts. It does not cover rate limits, auth requirements, or what a rejected/failed confirm looks like, so it stops short of a 5.

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 resource definition, then a tight action-by-action breakdown and a caveat about verified facts. Some redundancy exists ('put records a user assertion' vs 'Facts are insert-only: a put adds a new version'), but every sentence carries substantive information.

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

Completeness3/5

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

For a 12-parameter tool with no output schema, the description compensates by describing the returned source fields (step_id, job_id, url, fetched_at, tier, evidence) and the versioning model. However, several parameters (ttl_s, confidence, kind, system_of_record, limit) are left unexplained, which leaves gaps for an agent composing a put or a paged list call.

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?

At 75% schema coverage the schema already documents most parameters. The description adds relational meaning for subject/key/prefix/version selection, but leaves kind, as_of, ttl_s, confidence, limit, and system_of_record entirely to the schema with no added context.

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 resource and qualifier ('Evidence-backed fact store for the signed-in user (and organisation)') and then enumerates each action (get, history, put, confirm) with its distinct semantics. An agent can distinguish this from sibling store/hands tools without opening the schema.

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?

It gives clear conditional routing within the tool: 'pass subject and key for one, or subject/prefix to list', and explains the put-then-confirm workflow ('unconfirmed until the user confirms it'). It does not name when to prefer this over siblings like alterlab_store_get or alterlab_hands_answer, so no explicit alternatives are provided.

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

All mcp-server 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.