Skip to main content
Glama
Sign In

hedwigai

by com.hedwigai
OverviewDiscussionsAdmin

Stop a workbook's run

stop_run
DestructiveIdempotent

Stops the run editing a workbook — the one read_workbook shows as live_run, or the run_id you name. The run stops at once. What it had written by then is not thrown away: if it changed the document, it becomes a new version, unfinished, and the version before it is kept and restorable; if it changed nothing, no version is written. A drawn procedure stopped before it finishes writes nothing. With no run going, this says so and changes nothing.

Input Schema

NameRequiredDescriptionDefault
run_idNoThe run to stop. Omit for the workbook's live run.
contextNoExplain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
workbookYesThe workbook id.
llm_modelNoThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / context
      Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}
    • addedInput schema / properties / llm_model
      Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing post-conditions: partial output becomes an unfinished new version with the prior version kept and restorable, no version is written if nothing changed, and a drawn procedure writes nothing. This is exactly the kind of consequence detail destructiveHint=true cannot convey. The only gap is it never says what the call returns or how failure is signalled.

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 action and run selection, then layered consequences in short declarative sentences. Every sentence carries distinct information, though the version/restore detail is dense enough that a reader must parse three clauses to extract it.

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?

For a destructive mutation with full annotations and no output schema, the description covers trigger, selection, and side effects thoroughly. It stops short of describing the response payload or how a failed stop is reported, which matters somewhat given no output schema exists.

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% and the schema already documents run_id's omit-behaviour, workbook, and the analytics fields. The description's only added meaning is pointing at read_workbook as the way to obtain the live run id, so baseline 3 applies.

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 and resource ('Stops the run editing a workbook') and immediately disambiguates which run: the one read_workbook surfaces as `live_run`, or the named `run_id`. An agent can distinguish this from list_runs or restore_version without opening the schema.

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?

Gives clear operational context: omit run_id to target the live run, and the no-run case is explicitly described as a reporting no-op. It lacks explicit routing to alternatives (e.g. use restore_version to roll back afterwards, or list_runs to enumerate runs), so it falls short of full when/when-not guidance.

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

All hedwigai toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources