Skip to main content
Glama

Delete Recording

delete_recording
DestructiveIdempotent

Deletes a finished recording with its sidecar files and registry entries, then reports freed bytes. Requests user confirmation first when the client supports it.

Instructions

Delete a finished recording with its sidecars (event log, webcam, transcript, index, markers, pause parts) and registry entries; reports bytes freed. Asks the user first when the client supports it. Edits made from it are kept.

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": "delete_recording"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputNoOr the recording's path.
sessionIdNoSession id of the recording to delete.

Output Schema

NameRequiredDescriptionDefault
deletedYes
bytesFreedYes
outputPathYes
sessionsRemovedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.49.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true, but the description adds material detail beyond them: the exact scope of destruction including sidecars and registry entries, that bytes freed are reported, that a client-side confirmation prompt may occur, and the non-obvious retention rule that edits made from the recording survive. It stops short of stating irreversibility or any permission requirements.

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?

Two compact sentences, front-loaded with the destructive action and its full blast radius, followed by the safety and retention caveats. The parenthetical list is dense but each item carries real information about what disappears.

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 destructive two-parameter tool with an output schema (so return values need no explanation) and full annotation coverage, this description covers scope, side effects, confirmation behaviour, and data retention. An agent knows what will be gone and what will remain.

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% — both `input` (recording path) and `sessionId` are documented in the schema, and neither is required. The description adds no clarification about which identifier form to prefer or how the two interact, so it sits at the baseline where the schema does all 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 description opens with a specific verb and resource ("Delete a finished recording") and enumerates exactly what is removed — sidecars (event log, webcam, transcript, index, markers, pause parts) and registry entries. The word "finished" scopes it apart from recordings still in progress, which is the meaningful distinction among the siblings.

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?

Usage is only implied through the phrase "finished recording"; there is no explicit statement of when to choose this over related lifecycle tools, nor a statement of when not to call it. The confirmation note ("Asks the user first when the client supports it") is procedural behaviour rather than selection guidance.

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