Skip to main content
Glama

get_evaluation_results

Read-only

Retrieve one Otto / Now Assist evaluation run with per-metric pass/fail summaries, per-record results, and child runs to review outcomes.

Instructions

Get the results of one Otto / Now Assist evaluation run: the run (sys_one_extend_batch_run), per-metric results with a pass/fail summary (sys_one_extend_eval_metric_result), per-record results (sys_one_extend_batch_result) and child runs.

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": {
      "batch_run_sys_id": "<batch_run_sys_id>"
    },
    "name": "get_evaluation_results"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax metric/record rows (default 200)
include_recordsNoInclude per-record batch results (default true)
batch_run_sys_idYessys_id of the sys_one_extend_batch_run

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.0.1

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered and the description's contribution is the result composition: run record, per-metric pass/fail, per-record results, child runs. That is real added value, but it omits behavior that matters here: whether limit truncates and how an agent detects truncation, and what happens when the run is still in progress or has no results yet.

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?

A single front-loaded sentence that names the resource before parenthetically enumerating the tables involved. Dense but every clause carries information; the parenthetical table names aid precision without padding.

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

Completeness4/5

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

With no output schema, the description carries the burden of explaining return values and does so adequately by naming the four result components and their underlying tables. It is close to complete for a read-only single-run fetch, with the main shortfall being truncation/limit semantics and handling of incomplete runs.

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 three parameters (limit, include_records, batch_run_sys_id) are already documented in the schema, which sets the baseline at 3. The description's mention of 'per-record results' and 'child runs' loosely maps to include_records but adds no new syntax, defaults, or interaction detail beyond the schema.

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 ('Get the results') and a precisely scoped resource ('one Otto / Now Assist evaluation run'), then enumerates exactly which result tables are returned. The domain qualifier (Otto / Now Assist evaluation) separates it from sibling result tools such as get_survey_results or list_atf_test_results, though it never names an alternative.

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?

Usage is only implied: the phrase 'one ... evaluation run' plus a required batch_run_sys_id makes clear this is a single-run lookup rather than a listing or search. There is no explicit when-to-use, no prerequisites, and no statement of when another tool (e.g. a listing or trace tool) would be the better choice.

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