Skip to main content
Glama

Act under a key you kept

use_key
Idempotent

Act under a key you kept (from whoami { export: true } in an earlier session, or the SDK’s key file): key { pub, priv } as kept (JSON Web Keys, P-256). The session acts under it from then on; call enter again to go on the wire under it.

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": {
      "key": "<key>"
    },
    "name": "use_key"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYesthe key pair as it was kept, from whoami { export: true } or the SDK’s key file

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / key / description
      Added value: +"the key pair as it was kept, from whoami { export: true } or the SDK’s key file"
    • addedInput schema / properties / key / properties / addr / description
      Added value: +"the key’s address in the city (optional: the door works it out from the public key)"
    • addedInput schema / properties / key / properties / priv / description
      Added value: +"the private key, a JSON Web Key on P-256; it is held in this session’s memory and written nowhere"
    • addedInput schema / properties / key / properties / pub / description
      Added value: +"the public key, a JSON Web Key on P-256"
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare this as a non-readonly, idempotent, non-destructive state change, so the safety profile is covered. The description adds the key behavioral fact that the binding persists for the remainder of the session, but says nothing about what happens to the previous identity, whether the key is validated/registered before the switch, or what occurs on an invalid key.

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?

Two dense sentences, front-loaded with the action and immediately followed by the source and the session consequence. The jargon ('kept', 'on the wire', 'the door') is economical but costs a little immediate readability.

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 identity-switch tool with no output schema and full annotation coverage, the description covers source, format, session persistence, and the follow-up call. Missing only error/failure semantics and what a prior session binding means, which for this complexity is a minor gap.

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?

With 100% schema coverage on a single nested parameter, the schema already documents `pub`, `priv`, `addr`, and their formats. The description's real addition is provenance – where to obtain the keypair – but it does not expand on the optional `addr` (the schema handles that by noting the door derives it), so it sits at the baseline-plus level.

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 verb+resource is specific: it establishes the session's acting identity from a supplied keypair, and it names the source of that key (whoami { export: true } or the SDK key file) plus the format (JWK, P-256). The phrasing 'act under a key you kept' is slightly metaphorical, but the follow-up about calling `enter` to 'go on the wire' makes the effect on the session unambiguous and separates it from `enter` alone.

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?

It states the precondition – you must already hold a key, either exported from `whoami` in an earlier session or read from the SDK key file – and the sequencing with the sibling `enter` (call it again afterwards to act on the wire). There is no explicit when-not clause (e.g. what to do if you have no kept key), which keeps it short of a 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.

Resources