Skip to main content
Glama

TraceCheck

evaluate_trace

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, efficiency}, 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, repeated steps (loops), success claimed without evidence, 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 observed

TDQS

A4.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that evaluation is deterministic, offline, free, needs no API key, uses keyword heuristics rather than an LLM, and returns issues plus at most 5 suggestions. It even explains what low scores typically indicate. The one gap is side effects and data handling — agent_name is marked 'logging only', which hints at persistence without stating what is stored or whether the call itself is read-only.

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-loaded with the outcome and a WHEN TO CALL line, then organized under INPUT / RETURNS JSON / THE LOOP headings — easy to scan. It is on the long side, and the THE LOOP section is somewhat advisory rather than definitional, but no sentence is truly wasted given the 0% schema coverage it compensates for.

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?

There is no output schema, yet the description enumerates the returned JSON fields (score, five named dimensions, issues, suggestions max 5, summary, version). Combined with the four documented inputs, the trigger conditions, and the scoring caveats, an agent has everything needed to invoke this correctly on the first try.

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 compensate, and it does: each of the four parameters gets a dedicated bullet with expected format, an inline example trace line, and quality constraints (goals under 20 chars are penalised; traces must state what each tool returned, errors, retries, and a final 'Verified:' line). This is meaning well beyond bare 'type: string' fields.

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?

Opens with a specific verb and resource: 'Get an independent, deterministic reliability check of a multi-step task you just ran', then names the exact deliverable (0-100 score, issues, fixes). It is clearly distinguishable from the only sibling, get_trace_schema, which is explicitly framed as the format reference rather than the evaluator.

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?

The WHEN TO CALL block gives concrete trigger points: after finishing or giving up on a multi-step task, before reporting 'done', or after a failure worth learning from. It also routes to the sibling explicitly with 'Call get_trace_schema first if unsure of the format', and the THE LOOP section describes the iterative usage pattern.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.