Rokha

Read what a run actually did

trace_search

Read-only

List your Traces — the durable record of what a run DID, newest first. This is the other half of rig_run: a run reports that it started, and the trace is where the answer lands. Without it an agent can run a rig and never learn whether it worked, which makes the run untestable. Filter by rig_id (this rig's runs), parent_trace_id (the STEPS under one run — this is how you see which steps ran and which were skipped by a guard), trace_kind ('run' for the containers, 'atomic' for individual steps), run_id (every trace ONE run wrote — the id rig_run and POST /api/rigs/run return), node_id or status. Signed in: your own traces. Anonymous: pass run_id to read a PUBLIC rig's run (anyone holding the id may; the runner's identity is stripped). A private run answers not-found, never forbidden.

Input Schema

Name	Required	Description
`limit`	No	Newest N (default modest).
`rig_id`	No	Only traces from this rig.
`run_id`	No	One run's traces — the run id rig_run / POST /api/rigs/run hand back. Works anonymously for a PUBLIC rig's run.
`status`	No	e.g. success, error, partial.
`node_id`	No	One graph node's passes within a run.
`trace_kind`	No	'run' (containers) or 'atomic' (steps).
`parent_trace_id`	No	The atomic step traces under one run — how you see which steps actually ran.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

Changed2 schema fields changedSep 29, 2026

addedInput schema / properties / node_id

Added value: +{
+  "description": "One graph node's passes within a run.",
+  "type": "string"
+}

addedInput schema / properties / run_id

Added value: +{
+  "description": "One run's traces — the run id rig_run / POST /api/rigs/run hand back. Works anonymously for a PUBLIC rig's run.",
+  "type": "string"
+}

First observedSep 26, 2026

TDQS

A4.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is carried by structured data. The description adds genuinely useful context beyond that: ordering, the signed-in vs anonymous access model, that the runner's identity is stripped on public reads, and that a private run returns not-found rather than forbidden (an anti-enumeration detail an agent would otherwise misread as an error).

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 purpose is front-loaded and the filter list is dense with signal, but the prose is one long run-on paragraph with line-wrap artifacts mid-sentence, and the run_id explanation is given twice (once in the filter list, once in the anonymous sentence). The 'makes the run untestable' clause is motivational padding rather than operational information.

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?

With an output schema present, return values need no explanation, and the description covers the remaining burden for a 7-param, zero-required filter tool: every filter's purpose, the auth/anonymity model, privacy failure semantics, and default ordering. Nothing an agent needs to call it correctly is missing.

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

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description supplies intent the schema lacks: parent_trace_id is framed as 'the STEPS under one run' for spotting guard-skipped steps, run_id is tied to the exact value rig_run and POST /api/rigs/run return, and trace_kind is explained as containers vs steps. It also states that run_id works anonymously for public rigs, which is not derivable from the schema.

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 definition uses a specific verb and resource ('List your Traces') plus scope and ordering ('newest first'), and explicitly positions itself against the sibling rig_run as 'the other half' — the run reports start, the trace reports the outcome. An agent knows immediately this is the read-side inspection tool rather than the execution tool.

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

Usage Guidelines4/5

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

It states when to reach for it (to learn whether a rig run actually worked, and which steps a guard skipped) and names rig_run as the counterpart, plus when anonymous access applies and which filter to pass. The gap: it never mentions trace_get, so the choice between listing traces and fetching one trace is left to inference.

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

All Rokha tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.