hedwigai

See or change a workbook's settings

configure_workbook

Idempotent

A workbook's settings, and changes to them: its name; its mode — harnessroom, latticeroom or graphroom (a harnessroom researches and writes; a latticeroom is handed a draft and marks each claim with its sources, and each reference with whether the work exists, leaving the words as written; a graphroom performs the procedure drawn for it in the app); for a harnessroom, the model its runs think with (one of the nodes this answers with), the harness that drives it, the time a run gets — time_limit_minutes, or time_limit_seconds for a run someone waits on — and its economy; the members it belongs to; and the storage its runs file sources into. Send only what should change — the rest stays. With nothing to change it only reads. Changes apply from the next run.

Input Schema

TableJSON Schema

Name	Required	Description
`mode`	No	What this workbook's runs are, from now on. `harnessroom` (a new workbook's default): the instruction is a request, and a harness researches and writes the document. `latticeroom`: the instruction is a draft someone already wrote, whole — markdown, its links kept — which comes back exactly as written, with the run's inference beside it (read_workbook's `inference`: each claim cited, self-reported, secondary only, contradicted or with no source, and its sources); each entry under its References or Bibliography heading is looked up in Crossref and on the web and marked found, found with other authors or year, or not found, and a sentence citing it — [3], (Smith et al., 2020) — is read against the work found; attach data files (.json, .csv, .tsv) to settle the draft's own figures. `graphroom`: runs perform the procedure drawn for the workbook in the app, and refuse until one is drawn. Omit to keep the workbook's current mode.
`name`	No	A new name for the workbook.
`model`	No	The model a harnessroom's runs think with: a `node` from this tool's answer.
`context`	No	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."
`economy`	No	How a harnessroom run keeps its transcript small: compaction (the default), steering, delegation, or unbounded.
`harness`	No	The coding harness that drives a harnessroom run.
`members`	No	Every member's email, the whole list: who the workbook is shared with and who its email goes to.
`storage`	No	Where runs file the sources they save: a connected drive, or auto (the first connected).
`workbook`	Yes	The workbook id.
`llm_model`	No	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.
`time_limit_minutes`	No	How long a harnessroom run may take before it is stopped.
`time_limit_seconds`	No	The same in seconds, for a run a person waits on: stopped there, it delivers the draft it has written. Give this or time_limit_minutes, not both.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 16, 2026

removedInput schema / properties / preload_methods

Removed value: -{
-  "description": "Whether the methods the instruction names are put into a harnessroom run before it starts. On by default; false is for measuring what that does.",
-  "type": "boolean"
-}

Changed1 schema field changedOct 16, 2026

addedInput schema / properties / preload_methods

Added value: +{
+  "description": "Whether the methods the instruction names are put into a harnessroom run before it starts. On by default; false is for measuring what that does.",
+  "type": "boolean"
+}

Changed1 schema field changedOct 15, 2026

addedInput schema / properties / time_limit_seconds

Added value: +{
+  "description": "The same in seconds, for a run a person waits on: stopped there, it delivers the draft it has written. Give this or time_limit_minutes, not both.",
+  "maximum": 14400,
+  "minimum": 20,
+  "type": "integer"
+}

Changed1 schema field changedOct 14, 2026

changedInput schema / properties / mode / description

Previous value: -"What this workbook's runs are, from now on. `harnessroom` (a new workbook's default): the instruction is a request, and a harness researches and writes the document. `latticeroom`: the instruction is a draft someone already wrote, whole — markdown, its links kept — which comes back exactly as written, with the run's inference beside it (read_workbook's `inference`: each claim cited, self-reported, secondary only, contradicted or with no source, and its sources); attach data files (.json, .csv, .tsv) to settle the draft's own figures. `graphroom`: runs perform the procedure drawn for the workbook in the app, and refuse until one is drawn. Omit to keep the workbook's current mode."New value: +"What this workbook's runs are, from now on. `harnessroom` (a new workbook's default): the instruction is a request, and a harness researches and writes the document. `latticeroom`: the instruction is a draft someone already wrote, whole — markdown, its links kept — which comes back exactly as written, with the run's inference beside it (read_workbook's `inference`: each claim cited, self-reported, secondary only, contradicted or with no source, and its sources); each entry under its References or Bibliography heading is looked up in Crossref and on the web and marked found, found with other authors or year, or not found, and a sentence citing it — [3], (Smith et al., 2020) — is read against the work found; attach data files (.json, .csv, .tsv) to settle the draft's own figures. `graphroom`: runs perform the procedure drawn for the workbook in the app, and refuse until one is drawn. Omit to keep the workbook's current mode."

Changed6 schema fields changedOct 14, 2026

changedInput schema / properties / economy / description

Previous value: -"How a research run keeps its transcript small: compaction (the default), steering, delegation, or unbounded."New value: +"How a harnessroom run keeps its transcript small: compaction (the default), steering, delegation, or unbounded."

changedInput schema / properties / harness / description

Previous value: -"The coding harness that drives a research run."New value: +"The coding harness that drives a harnessroom run."

changedInput schema / properties / mode / description

Previous value: -"What this workbook's runs do, from now on. `research` (a new workbook's default): the instruction is a request, and the run finds sources and writes the document. `ground`: the instruction is a draft someone already wrote, whole — markdown, its links kept — and the run leaves every word as written and marks each claim cited (with the passage quoted), self-reported, secondary only, contradicted or with no source. Link data files on the account's drive (/dropbox/...json, .csv) in the draft to settle its own figures. Omit to keep the workbook's current mode."New value: +"What this workbook's runs are, from now on. `harnessroom` (a new workbook's default): the instruction is a request, and a harness researches and writes the document. `latticeroom`: the instruction is a draft someone already wrote, whole — markdown, its links kept — which comes back exactly as written, with the run's inference beside it (read_workbook's `inference`: each claim cited, self-reported, secondary only, contradicted or with no source, and its sources); attach data files (.json, .csv, .tsv) to settle the draft's own figures. `graphroom`: runs perform the procedure drawn for the workbook in the app, and refuse until one is drawn. Omit to keep the workbook's current mode."

changedInput schema / properties / mode / enum

Previous value: -[
-  "research",
-  "ground"
-]New value: +[
+  "harnessroom",
+  "latticeroom",
+  "graphroom"
+]

changedInput schema / properties / model / description

Previous value: -"The model research runs think with: a `node` from this tool's answer."New value: +"The model a harnessroom's runs think with: a `node` from this tool's answer."

changedInput schema / properties / time_limit_minutes / description

Previous value: -"How long a research run may take before it is stopped."New value: +"How long a harnessroom run may take before it is stopped."

AddedOct 14, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: partial-patch semantics, that edits take effect only from the next run, and that `graphroom` mode runs refuse until a procedure is drawn.

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?

The core instruction (partial update, read-only when empty, next-run effect) is front-loaded, but the mode enumeration is a long nested run-on that duplicates the schema's own mode description, diluting the structural clarity of an otherwise well-organized entry.

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 12-parameter mutation tool with no output schema, the description covers when it writes, when it reads, when changes apply, and mode-specific preconditions. It gestures at the return value via "one of the `nodes` this answers with" but never states what a read call returns or what permissions are required.

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% across all 12 parameters, so the schema already carries the semantics and the baseline is 3. The prose mostly restates the mode enum and the model/time fields that the schema already documents in comparable depth, adding little beyond it.

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 pair and resource: reading and changing a workbook's settings, with an enumerated list of what is configurable. However, it never distinguishes itself from the sibling `update_workbook`, leaving the agent to infer which settings tool applies.

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: "Send only what should change — the rest stays. With nothing to change it only reads. Changes apply from the next run," which resolves the read-vs-write ambiguity inherent to a get/set tool. No exclusions or sibling alternatives are named, so it stops short of a 5.

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

All hedwigai tools Inspect

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.

See or change a workbook's settings

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources