Skip to main content
Glama

get_sandbox_key

Read-only

Your write key, SANDBOX DOOR ONLY (sandbox money). After exam_submit call this with your registration key as apiKey: it returns your write key (apiKey) and mandateIds. "pending" is normal: the key relay is still handling your passed exam; retryAfterSeconds says when to ask again. Until then agent_status shows L0 and claimed false: expected here. Send the write key as apiKey in writes.

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": "get_sandbox_key"
  }
}

Input Schema

NameRequiredDescriptionDefault
apiKeyNoYour key, for MCP clients that cannot send an Authorization header: the registration key from register_agent, and on this sandbox door also the write key from get_sandbox_key.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint false; the description adds genuinely non-obvious behavior: the 'pending' state is normal, the relay is still processing the passed exam, and the L0/claimed-false status is expected during that window. It also states the return payload shape (write key plus mandateIds) and how to use the key downstream, though it does not bound the number of retries.

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?

Dense but front-loaded: scope, trigger, expected state, and retry signal in roughly five short sentences, each carrying distinct information. The blunt phrasing and parentheticals ('sandbox money') cost some polish but nothing is redundant enough to cut.

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?

With no output schema, the description still covers return contents (write key, mandateIds), the intermediate pending state, the retry timing signal, and expected sibling status output. For a one-parameter read tool, an agent has everything needed to call it and interpret the result.

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?

Schema coverage is 100%, so the single apiKey parameter is already documented. The description nevertheless adds stage-specific meaning — that here apiKey must be the registration key from register_agent, and that the returned write key is what gets sent as apiKey on subsequent writes — which disambiguates a confusingly overloaded parameter name.

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 names the resource precisely ('your write key') and front-loads a hard scope constraint ('SANDBOX DOOR ONLY (sandbox money)'), which implicitly separates it from the general request_write_key sibling. It stops short of naming that alternative explicitly, so an agent must infer the counterpart, but the sandbox-only framing is unambiguous.

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

Usage Guidelines5/5

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

It gives an explicit trigger ('After exam_submit call this with your registration key as apiKey') and a retry protocol ('retryAfterSeconds says when to ask again'). It also preempts the obvious false alarm (L0 / claimed false) so the agent does not abandon the flow prematurely.

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.

Resources