TeamShared

process_run_get

Fetch one Process run (snapshot, current step, standing, work, stream_id).

standing is a projection over run:{id} events (true / changed / next / owner / blocked / since / due / timeout). It is not a writable column — draft with process_run_standing_draft and commit with process_run_standing_commit. Pass source=events to fold the run object from the log alone (no process_runs read).

Input Schema

TableJSON Schema

Name	Required	Description
`run_id`	Yes	Process run UUID
`source`	No	row (default) reads process_runs; events reconstructs the run from stream_events on run:{id} only
`context`	No	Also return a capped context pack: stage and step guidance, the subject, evidence gaps, the recent timeline and cost so far. Use it to resume a long-running instance.
`context_max_chars`	No	Cap for the context pack (default 6000)

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 15, 2026

addedInput schema / properties / context

Added value: +{
+  "default": false,
+  "description": "Also return a capped context pack: stage and step guidance, the subject, evidence gaps, the recent timeline and cost so far. Use it to resume a long-running instance.",
+  "type": "boolean"
+}

addedInput schema / properties / context_max_chars

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 30000,
+      "minimum": 1000,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Cap for the context pack (default 6000)"
+}

Changed1 schema field changedSep 16, 2026

addedInput schema / properties / source

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "row (default) reads process_runs; events reconstructs the run from stream_events on run:{id} only"
+}

AddedSep 10, 2026

TDQS

A3.7/5.0

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 delivers: it explains standing is a read-only projection over run:{id} events rather than a writable column, and that source=events folds from the log without touching process_runs. Auth/permission behavior is not covered, which is a minor gap.

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-loads the purpose in the first clause, then adds the standing caveat and source note. Efficient, though the standing bullet list (true/changed/next/...) is somewhat dense for the return-value detail an output schema already carries.

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?

Output schema exists, so listing return fields is mild redundancy, but the description still supplies the semantic layer an agent needs (read-only standing, event-folding source, context pack for resuming). Complete enough for a 4-param read tool with full schema coverage.

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 coverage is 100%, so all four parameters are already documented. The description restates the value of source=events ("no process_runs read") and clarifies the standing field, adding only marginal meaning beyond the schema, consistent with the baseline 3.

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 clear verb+resource ("Fetch one Process run") and enumerates the payload shape (snapshot, current step, standing, work, stream_id). The singular "one" implicitly distinguishes it from process_run_list, though it does not name that sibling outright.

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?

Gives a useful when-not-to-use rule for the standing field (draft/commit instead of writing here), but offers no explicit guidance on choosing this over process_run_list, process_run_events, or the context flag toggle. Usage is implied rather than stated.

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

All TeamShared tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold 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.