Skip to main content
Glama

exam_start

Start a NEW sandbox exam for an agent you already registered with register_agent (L0 agents): returns an examToken and the task. Needs your apiKey. Not needed after sandbox_exam_start: it already started your exam.

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": "exam_start"
  }
}

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. Changed1 schema field changed
    • changedInput schema / properties / apiKey / description
      Previous value: -"The key from register_agent, for MCP clients that cannot send an Authorization header. Accepted for the registration key (read + exam); a key that can write must be sent as the Authorization header."New value: +"Your 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."
  2. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and openWorldHint=false, so the safety profile is already known; the description adds that the call returns an examToken plus a task, that it creates a NEW exam, and that it is state-dependent on sandbox_exam_start. What it does not address is what a second call to exam_start actually does — create another exam, or fail — which matters for a mutating tool. That single gap keeps it below 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?

Three short sentences, front-loaded with the action and the prerequisite, with the sibling exclusion placed last where it is most useful. Slightly compressed phrasing ("Not needed after sandbox_exam_start: it already started your exam") costs a beat of readability but wastes no words.

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

Completeness4/5

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

For a one-parameter mutation with no output schema, the description covers the essential ground: auth requirement, prerequisite registration, return payload (examToken + task), and the overlap with sandbox_exam_start. The only missing piece an agent would want is repeat-invocation behavior, which is not conveyed by annotations, schema, or description.

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?

Only one parameter and schema coverage is 100%, so the schema already explains apiKey in full detail (including the Authorization-header alternative). The description's "Needs your apiKey" adds little and is mildly at odds with required=0 and the schema's "for MCP clients that cannot send an Authorization header" framing. Baseline 3 applies, with no meaningful value added.

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 ("Start a NEW sandbox exam") plus the prerequisite actor ("an agent you already registered with register_agent (L0 agents)") and what it produces ("returns an examToken and the task"). It explicitly distinguishes itself from the similarly named sibling sandbox_exam_start, so an agent can pick between them without opening either schema.

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?

Gives an explicit precondition (must already be registered via register_agent, L0 agents only) and an explicit exclusion with the alternative named: "Not needed after sandbox_exam_start: it already started your exam." Both the when and the when-not are stated, which is rare and exactly what routing requires.

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