Skip to main content
Glama

osirAgentDelete

Destructive

osirAgentDelete: Stage removal of the user's AI agent (e.g. Hermes). DESTRUCTIVE: stops and removes the agent from the user's VPS. Its data folder (conversations, memories) stays on the VPS, and the VPS itself is NOT cancelled (that is deleteVpsInstance). Returns an actionId; present the summary and call executeConfirmedAction only if the user approves. Requires authentication.

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": {
      "agentId": "<agentId>"
    },
    "name": "osirAgentDelete"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentIdYesAgent id from osirAgentList.
sessionKeyNoSession key (osk_...) returned by checkDeviceLoginStatus. Pass it on every call when logged in via the in-chat device flow; omit when connected via OAuth.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description goes well beyond them: it discloses that the agent is stopped and removed but its data folder (conversations, memories) remains on the VPS, that the VPS survives, and that the call is staged rather than immediate. The comma-separated 'data folder ... stays' detail is exactly the destructive-radius information an agent needs before confirming with a user.

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

Conciseness5/5

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

Front-loaded with the destructive warning and the identifier prefix, then side effects, then the confirmation contract, then the auth note. Every clause carries distinct information; nothing is repeated from the title or annotations verbatim.

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?

For a two-parameter destructive tool with no output schema, the definition covers everything an agent needs: what is destroyed, what is retained, what must be confirmed, how the return value is used, and the auth requirement. No meaningful gap remains.

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?

Schema description coverage is 100%, so agentId's origin (osirAgentList) and the sessionKey guidance are already documented in the schema. The description adds no field-level meaning beyond that, which is the expected baseline when the schema does the work.

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?

The first sentence names a specific verb and resource ('Stage removal of the user's AI agent') and even gives a concrete example (Hermes). It explicitly demarcates scope from siblings by stating the VPS is not cancelled 'that is deleteVpsInstance', so an agent can distinguish this from the other delete tools without opening a 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?

It lays out the two-step flow explicitly: this call stages the removal and returns an actionId, and executeConfirmedAction should only be called after user approval. It also names the adjacent operation to use instead when the intent is cancelling the VPS (deleteVpsInstance) and states the auth precondition.

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.