Skip to main content
Glama

performance_profile

Destructive

Start or stop a Cfx profiler frame recording and save the session, returning a profile ID to analyze resource performance.

Instructions

Start a Cfx profiler recording (frames), or stop and save it. Pass the returned profile ID to performance_get_resource.

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": {
      "action": "<action>"
    },
    "name": "performance_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
framesNo
serverNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the description need not restate safety. It adds useful behavior (a profile ID is produced and consumed elsewhere) but never explains the destructive aspect made salient by the annotation, nor profiling overhead, permissions, or whether a new 'start' discards an in-flight recording.

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 tight sentences with the capability stated first and the cross-tool handoff second; no filler. Slightly compressed to the point of dropping needed detail, but nothing is redundant.

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?

For a 3-parameter, destructive-capable mutation tool with no output schema, the definition covers the basic start/stop cycle and the ID handoff. It omits what 'stop' actually produces (where the profile is saved), whether frames is ignored on stop, and any server-targeting semantics.

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%, so the description must carry the parameter burden. It mentions 'frames' only in passing and never clarifies that frames applies solely to 'start', what the 20-2000 range or default of 300 means practically, or what the 'server' parameter selects.

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?

Names a specific verb+resource pair ('Cfx profiler recording') and covers both modes (start / stop-and-save), plus the handoff of the returned ID to performance_get_resource. It stops short of naming unrelated siblings like performance_get, but the profiler scope is unambiguous.

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?

The 'start ... or stop and save' phrasing implies when each action applies, and it routes the agent to performance_get_resource for reading results. It gives no explicit trigger conditions (e.g. when to profile at all), no prerequisites, and no when-not guidance.

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