ContextLayer

log_trace

Log a granular agent action trace. High-frequency, no LLM processing.

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": {
      "trace_type": "<trace_type>",
      "summary": "<summary>"
    },
    "name": "log_trace"
  }
}

Input Schema

Name	Required	Description
`status`	No	Status: started, completed, failed (default: completed)
`summary`	Yes	Short description of the action
`task_id`	No	Task ID to link this trace to (optional — auto-links session to task)
`metadata`	No	Free-form JSON metadata (optional)
`trace_id`	No	Logical trace group ID (auto-generated if omitted)
`project_id`	No	Project ID (optional, alternative to project_name)
`session_id`	No	Session ID (optional — auto-resolved from project if omitted)
`trace_type`	Yes	Trace type: tool_call, file_read, file_write, code_search, code_edit, api_call, thinking, error
`duration_ms`	No	Duration in milliseconds (optional)
`project_name`	No	Project name (optional, used for auto-session resolution)
`parent_trace_id`	No	Parent trace ID for nesting (e.g. tool_call -> file_reads)

Schema Changelog

Changes observed during successful MCP inspections.

First observedMay 5, 2026

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations provided, the description must disclose behavioral traits on its own. It adds 'High-frequency, no LLM processing,' which is useful, but it omits critical behavior such as whether the trace is persisted, what side effects occur (e.g., auto-linking session/task from schema), or any latency or failure semantics. The description is sparse for a logging tool that creates records.

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?

The description is extremely concise: two short sentences that front-load the purpose and add a key behavioral trait. It is efficiently written without redundant words. A small deduction because 'granular' and 'high-frequency' are slightly vague, but overall it earns its place.

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

Completeness2/5

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

The tool has 11 parameters, no output schema, and no annotations, so the description must provide more context. It fails to mention parameter relationships like auto-linking of session/task, when to use vs siblings, or expected return behavior. The current description is too sparse to fully guide an agent, especially with sibling tools like log_activity and log_traces_batch present.

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 all 11 parameters are documented in the schema. The description adds no extra parameter information beyond what is already present. Baseline 3 is appropriate because the schema carries the semantic load, and the description does not clarify parameter usage (e.g., auto-resolution behavior of task_id/session_id).

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 uses a specific verb+resource: 'Log a granular agent action trace,' which clearly states the tool's core purpose. It distinguishes from siblings like log_traces_batch by noting 'granular' and 'High-frequency,' implying this is for individual, low-overhead traces. However, it does not explicitly differentiate from log_activity, which is a nearby sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance is given about when to use this tool versus alternatives. The phrases 'High-frequency, no LLM processing' provide context but do not name alternative tools or describe conditions for choosing this over log_traces_batch or log_activity. An agent would be uncertain about when this is the appropriate logging call.

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

All ContextLayer tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?