Starmux

get_recent_tool_calls

Read-only

Retrieve recent local tool call history with arguments and outputs to restore context, onboard new chats, or debug call sequences.

Instructions

                    Get recent local tool call history with arguments and outputs.
                    Returns a chronological list of recent calls loaded from the local history file.
                    
                    Useful for:
                    - Onboarding new chats about work already done
                    - Recovering context after chat history loss
                    - Debugging tool call sequences
                    
                    Note: Does not track its own calls or track_ui_event.
                    History is persisted locally in tool-history.jsonl, keeps up to the last 1000
                    calls in memory, and trims older on-disk history. Stored outputs over 4 KiB
                    are replaced with an omission marker.
                    
                    This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

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": "get_recent_tool_calls"
  }
}

Input Schema

Name	Required	Description	Default
`since`	No
`toolName`	No
`maxResults`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.16.2Nov 7, 2026

TDQS

A4/5.0

Behavior5/5

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

Annotations already declare readOnly/openWorld=false/destructive=false, yet the description adds substantial behavior beyond them: it excludes its own calls and track_ui_event, names the persistence file, states the 1000-call in-memory cap, notes disk trimming, and discloses the 4 KiB output omission marker. That is exactly the kind of context annotations cannot carry.

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?

Front-loads the core behavior, then structures the rest into a short bullet list and a compact behavior note. The trailing line about being referenced as 'DC: ...' is meta rather than functional for selection, but overall it is tight and every functional sentence earns its place.

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 read-only history reader with no output schema and no siblings to distinguish, the description covers what it returns (chronological argument/output list), storage lifetime, size limits, and self-exclusion. The only real gap is parameter meaning, which is a separate dimension.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and none of the three parameters (since, toolName, maxResults) are mentioned in the description. The phrase 'recent' vaguely hints at date ordering, but there is no explanation of filtering by tool name, the date format, or the result cap, so the description does not compensate for the coverage gap.

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?

States a specific verb+resource ('Get recent local tool call history with arguments and outputs') and clarifies returns a chronological list from a local history file. No sibling covers call history, so there is no overlap to disambiguate, but it also does not explicitly contrast with any sibling.

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?

The 'Useful for' bullets give concrete contexts (onboarding chats, recovering context after history loss, debugging tool call sequences), which is clear usage guidance. It lacks an explicit when-not-to-use or alternative-tool clause, so it stops 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.

Deploy Server