Skip to main content
Glama

Look around

look
Read-only

The room you are in, where you stand and which way you face, how many dollars you hold, the people nearest you with what they are saying (and whether they are typing, or that they are editing or reading), its doors (those leading nowhere only in your own room), the dollar bills lying about, the cannon balls in the air (where each is, and how many cells it goes a second), the things placed nearest you (a cannon with whether it is on and its balls left), and its restricted zones.

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": "look"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior3/5

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

The readOnlyHint annotation already establishes this is a non-mutating observation, and nothing in the description contradicts that. Beyond the annotation, the description does add real behavioral detail — notably that doors leading nowhere are visible only in your own room, and that restricted zones are reported — which is context the annotations do not carry. However, cryptic phrasing ('how many cells it goes a second', 'a cannon with whether it is on and its balls left') leaves the actual semantics of several reported fields unclear, and it says nothing about range limits on 'nearest you' or whether looking consumes a turn.

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

Conciseness3/5

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

It is compact and front-loads the room and your own position before moving outward to people, objects, and projectiles, which is a sensible ordering. But the whole thing is a single sprawling noun list with no verbs or delimiters, so it reads as a run-on and forces re-parsing; a short leading clause plus a structured list would convey the same content far more cheaply.

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?

There is no output schema and no parameters, so the description must carry the return-value burden, and it does list the observable categories — that is the right instinct. Gaps remain: the meaning of several listed fields is opaque, and there is no indication of scope limits (how far 'nearest' reaches) or what is omitted from view. Adequate for a parameterless observation tool, but not fully self-explanatory.

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?

The tool takes zero parameters, so there is no parameter meaning for the description to add; baseline 4 applies. The description correctly implies a parameterless snapshot of current state rather than a targeted query.

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 enumerates specifically what an observation yields: room identity, position and facing, money held, nearby people and their speech/typing/editing state, doors, loose dollar bills, cannon balls in flight with velocity, nearest objects, and restricted zones. That is a concrete, distinctive resource set that separates it from siblings like inventory or room_settings. It loses a point because there is no verb framing the enumeration, and the overlap with 'how many dollars you hold' (inventory) and room/object details (room_settings, look_blocks) is left unresolved.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is only implied: the tool obviously means 'observe current surroundings', and the content list lets an agent infer when it is useful. There is no explicit statement of when to prefer it over inventory, room_settings, appearance, or look_blocks, and no note about cost, cooldown, or frequency of use. An agent can guess correctly, but the definition does no routing work.

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.