Skip to main content
Glama

world_history

Read a room's append-only log of successful ops, oldest first, up to 500 rows: one line per row, seq agent type entity result (create, edit, remove, fork, propose, accept, reject...). Propose rows carry the p_ proposal id that world_accept and world_reject take. Filter with entity (one entity id) and after (to read only newer rows). Read-only, no token. Optional room (default: your current room). For the current state, use world_look.

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": "world_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
roomNo
afterNo
entityNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it declares read-only, no token required, append-only semantics, oldest-first ordering, a 500-row cap, and the per-row field shape (seq, agent, type, entity, result) including that propose rows embed a p_ id. The main gap is what happens when more than 500 rows exist and how to page past the cap beyond the implicit use of 'after'.

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 action, then filters, then the alternative sibling, so the agent can stop reading early. It is dense with parentheticals ('seq agent type entity result (create, edit, remove, fork, propose, accept, reject...)'), which is efficient but slightly cryptic as a compact listing.

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 specifies the return format (one line per row with named fields) and the row cap, so an agent knows what comes back. Combined with the read-only/no-token disclosure and the pointer to world_look, nothing essential for correct invocation 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 description coverage is 0%, so the description must compensate, and it does: room is optional with a default of the current room, after reads only newer rows, and entity restricts to a single entity id. Every parameter's meaning is explained beyond the bare JSON types and patterns.

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 ('Read a room's append-only log of successful ops') plus scope (oldest first, up to 500 rows, one line per row) and explicitly contrasts with the sibling world_look for current state. An agent can distinguish it from world_look and world_room 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 Guidelines4/5

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

Gives a clear when-to-use-this-instead signal ('For the current state, use world_look') and explains the filtering levers (entity for one entity, after for newer rows). It also links proposal ids to world_accept/world_reject. It stops short of stating when NOT to use it more broadly (e.g., auditing vs. asset inspection), keeping it a 4 rather than 5.

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.