Skip to main content
Glama

Physical Capability Cloud

pcc_onboard_session_build_agent

Finalise a physical-operator onboarding session. It mints no wallet, and it can't register the operator yet: its register call sends no API key, so the gateway refuses it and this call answers 500 build_failed with the refusal in message. A retry repeats the same refused call. Auth-required.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

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

Input Schema

NameRequiredDescriptionDefault
idYesSession id returned by pcc_onboard_session_start.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior5/5

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

With readOnlyHint=false and destructiveHint=false already supplied, the description still adds substantial undisclosed behavior: no wallet is minted, the register call carries no API key, the gateway refuses it, the call returns HTTP 500 with code build_failed, and the refusal text lands in `message`. It also flags that retries are futile and that auth is required, which is exactly the operational context an agent cannot get from the annotations.

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?

Four short sentences, front-loaded with the purpose and then the failure mode, with no filler or marketing language. The refusal is described twice (the gateway refuses it, and the refusal appears in `message`), but the second mention adds the response-shape detail, so the redundancy mostly earns its place.

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?

No output schema exists, so the description must carry return behavior, and it does: 500 with build_failed and the refusal in `message`. For a one-parameter tool this covers nearly everything an agent needs, though it never states whether anything is persisted or mutated before the failure — relevant given readOnlyHint=false.

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?

There is a single required parameter with 100% schema description coverage, so the schema already explains that `id` is a session id from pcc_onboard_session_start. The prose adds no additional meaning about format, validity, or what happens if the id is stale — baseline 3 applies when the schema carries the load.

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 opens with a specific verb and resource ("Finalise a physical-operator onboarding session") and names the sibling that produces its input (pcc_onboard_session_start), which separates it from the other session tools. It loses a point because the stated purpose is immediately negated: the agent is told the call cannot actually register the operator, so what the tool positively accomplishes is left unclear.

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?

It gives one explicit usage signal, negative but actionable: a retry repeats the same refused call, so do not retry. What is missing is the routing half — it never names what to do instead to complete operator registration, so the agent knows to avoid this call but not what to substitute.

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.