Skip to main content
Glama

evaluate_trace

Run an independent reliability check on an agent's multi-step task trace to get a 0-100 score, detected issues, and concrete fixes for the next attempt.

Instructions

Get an independent, deterministic reliability check of a multi-step task you (an agent) just ran. Returns a 0-100 score, the issues found, and concrete fixes to apply on your next attempt.

WHEN TO CALL: after you finish (or give up on) a multi-step task that used tools, before you report "done" to the user, or after a failure you want to learn from. Free, no API key, fast and offline (keyword heuristics, no LLM). Call get_trace_schema first if unsure of the format.

INPUT (all plain strings):

  • goal: the original task, stated specifically (what success looks like). Vague goals under 20 chars are penalised.

  • trace: your chronological steps, one per line, e.g. "1. Called search_flights(AMS->LIS) -> returned 3 results" / "2. Observed: ..." . Write what each tool RETURNED ("observed", "returned", "result:"), any error and the retry/fallback you used, and a final "Verified: ..." line.

  • outcome: the concrete final result you claim, and how it meets the goal.

  • agent_name: optional identifier for yourself (logging only).

RETURNS JSON: score (int 0-100), dimensions {goal_clarity, observability, error_recovery, goal_alignment}, issues (list), suggestions (list, max 5), summary, version.

THE LOOP: run task -> evaluate_trace -> apply the suggestions to your process -> re-run -> evaluate_trace again and compare scores/dimensions. Scores below ~60 usually mean missing observations, unrecovered errors, or no verification step.

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": {
      "goal": "<goal>",
      "trace": "<trace>",
      "outcome": "<outcome>"
    },
    "name": "evaluate_trace"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalYes
traceYes
outcomeYes
agent_nameNounknown

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.7/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it discloses behavior that matters for an eval tool: free, no API key, offline keyword heuristics with no LLM, deterministic output, and a fixed return shape. It adds a useful scoring interpretation anchor (below ~60 usually means missing observations, unrecovered errors, or no verification step). It never explicitly states whether submitted traces are stored or retained, even though it calls agent_name 'logging only', which implies some persistence.

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 text is long but organized under labeled sections (WHEN TO CALL, INPUT, RETURNS JSON, THE LOOP), with the core value proposition front-loaded. A few lines, such as the loop description, could be compressed, but nearly every sentence adds actionable detail.

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?

Although there is no output schema, the description enumerates the returned fields (score, four dimensions, issues, suggestions capped at 5, summary, version), and it fully specifies the three required string parameters and how to format them. An agent can call it correctly and interpret the result without further information.

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

Parameters5/5

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 all parameter meaning, and it does: goal must be specific because vague goals under 20 chars are penalized; trace is a chronological one-step-per-line format with example syntax and explicit instructions to record returns, errors, retries, and a final 'Verified:' line; outcome is the claimed result plus goal fit; agent_name is optional and used only for logging.

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 first sentence names a specific verb and resource: an independent, deterministic reliability check of a multi-step agent task, returning a 0-100 score plus issues and fixes. It is clearly distinguishable from the only sibling, get_trace_schema, which is explicitly positioned as the schema-lookup alternative.

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

Usage Guidelines5/5

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

It has an explicit 'WHEN TO CALL' section with temporal triggers (after finishing or giving up, before reporting done, after a failure you want to learn from) and points to get_trace_schema as the prerequisite when the format is unknown. It also describes the intended iterative loop: evaluate, apply suggestions, re-run, and compare.

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

Deploy Server

Other Tools