Whisper

agents: revoke

whisper_agents_revoke

The revoke operation on the Whisper control plane, served as CALL whisper.agents({op:'revoke', args:{...}}). Requires your Whisper API key. The identifier in the example is a placeholder for one of YOUR agents: list them with the "agents.list" skill and {"kind":"agents"}. Example call: {"skill":"agents.revoke","input":{"agent":"agent-a1f4c0b2d3e4f5a67"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.

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": {
      "input": "<input>"
    },
    "name": "whisper_agents_revoke"
  }
}

Input Schema

Name	Required	Description	Default
`input`	Yes	Arguments for this operation, as an object. The example passes {"agent":"agent-a1f4c0b2d3e4f5a67"}.

Output Schema

Name	Required	Description
`rows`	Yes	The answers, one object per row, keyed by the column names above. An empty array means the question was understood and nothing matched, which is an answer and not a failure.
`columns`	Yes	The column names, in order. Every row object has exactly these keys, so this is the row shape and reading it is cheaper than inspecting a row.
`statistics`	No	What the query cost.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false and openWorldHint=true, and the description adds genuinely useful context about auth methods and that the identifier must be one of the caller's own agents. However, it never says whether revocation is reversible, what happens to the agent's existing tokens/connections, or whether the call fails for already-revoked agents — significant gaps for a state-changing operation. There is mild tension with destructiveHint=false given that 'revoke' implies removing access, but it's plausibly a recoverable state change rather than an outright contradiction.

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

Conciseness3/5

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

Purpose is front-loaded, but the description is cluttered: it mixes a pseudo-call signature ('CALL whisper.agents({op:'revoke', args:{...}})') with a JSON example that convey the same thing, and it states the API-key requirement twice (opening sentence and closing OAuth/X-API-Key sentence). Tightening would improve scanability.

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

Completeness3/5

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

An output schema exists, so return values need not be explained, and auth plus identifier discovery are covered. Still missing for a mutation tool are the effects of the operation and irreversibility, which leaves the agent unable to predict consequences before invoking it.

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% and only one nested object is required, so the schema already carries most of the burden. The description still adds real value by showing the exact shape of the agent identifier and explaining where to obtain a valid value via agents.list, which the schema's placeholder text does not operationalize.

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 a specific verb ('revoke') and, via the call syntax and example, the resource (an agent on the Whisper control plane). It falls short of saying precisely what revocation means operationally (deleting the agent, invalidating its credentials, or disabling it), and it doesn't contrast with siblings like whisper_agents_disconnect beyond naming agents.list as a discovery step.

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 gives a concrete precondition chain: list your agents with the 'agents.list' skill using {"kind":"agents"} to obtain a real identifier, and it states the auth requirement (linked Whisper account via OAuth or X-API-Key header). What's absent is guidance on when revocation is the right action versus alternatives such as disconnect or token rotation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Whisper tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.