Skip to main content
Glama

Rokha

by ai.rokha
OverviewDiscussionsAdmin

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

TableJSON Schema
NameRequiredDescriptionDefault
limitNoNewest N (default modest).
rig_idNoOnly traces from this rig.
run_idNoOne run's traces — the run id rig_run / POST /api/rigs/run hand back. Works anonymously for a PUBLIC rig's run.
statusNoe.g. success, error, partial.
node_idNoOne graph node's passes within a run.
trace_kindNo'run' (containers) or 'atomic' (steps).
parent_trace_idNoThe atomic step traces under one run — how you see which steps actually ran.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • 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"
+}
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes well past the readOnlyHint/destructiveHint annotations with non-obvious behavior: ordering (newest first), signed-in vs anonymous access rules, that anyone holding a public run_id may read with identity stripped, and that private runs return not-found rather than forbidden. That auth/visibility nuance is exactly the context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, but the body is padded with rhetorical asides ('which makes the run untestable') and carries stray whitespace artifacts. The parameter explanations are dense but the text is longer than it needs to be.

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 does the heavy lifting on filtering, ordering, and access semantics, which is largely sufficient. It stops short of describing the returned trace shape/fields, the one remaining gap for a list tool.

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 is 3, but the description adds meaning beyond the schema by linking parent_trace_id to skipped-by-guard steps and run_id to the value rig_run returns. It enriches several parameters rather than restating them.

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?

States a specific verb+resource ('List your Traces — the durable record of what a run DID, newest first') and crisply positions itself against the sibling rig_run ('the other half of rig_run'). An agent immediately knows this is the read-side answer to a run's outcome.

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?

Explains when this is needed ('Without it an agent can run a rig and never learn whether it worked') and gives concrete filter-driven use cases (parent_trace_id to see which steps a guard skipped, run_id for one run). It never names the sibling trace_get as the single-trace alternative, so it stops short of explicit alternatives.

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

All Rokha toolsInspect
Try in Browser
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources