Skip to main content
Glama

hedwigai

by com.hedwigai
OverviewDiscussionsAdmin

Edit a workbook directly

write_workbook

Writes a new version of a workbook yourself, with no run and no charge. Send base_version — the version you read — and EXACTLY ONE of document (the whole text of a one-tab workbook) or sheets (the tabs, in their new order: {id} alone keeps a tab unchanged, {id, markdown} and/or {id, name} replaces what you give, {name, markdown} with no id adds a tab, and a tab you leave out is removed). note is one line on what changed and labels the version. Every write is a new version by this account; the one before is kept and can be restored. Refused if the workbook has moved past base_version or a run is writing it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNoOne line on what changed, e.g. 'Updated Q3 cash from the 10-Q'.
sheetsNoEvery tab in its new order. Tab ids come from read_workbook's `tabs`.
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."
documentNoThe new text of a one-tab workbook.
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.
base_versionYesThe version you read and changed.

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

A4.7/5.0
Behavior5/5

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

Annotations only give the safety profile (readOnly=false, destructive=false, idempotent=false); the description goes far beyond, disclosing the versioning model (every write is a new version, the prior one is kept and restorable), the refusal conditions (workbook moved past base_version or a run is writing it), and that there is no charge. This is exactly the extra behavioral 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.

Conciseness4/5

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

Front-loaded with the core action and cost, then the required inputs and semantics; every sentence carries weight. The nested sheets parenthetical is dense and somewhat hard to parse in one pass, which is a minor structural cost rather than filler.

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?

For a 7-parameter mutation tool with no output schema, the description covers the operation, the two required inputs, the document/sheets exclusivity, tab semantics, versioning, and refusal cases. The remaining analytics params (context, llm_model) are self-documented in the schema, so nothing an agent needs to call correctly is missing.

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

Parameters5/5

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

Schema coverage is 100%, so baseline is 3, but the description substantially exceeds it by explaining the sheets combination logic that the schema only lists field-by-field: {id} alone keeps a tab unchanged, {id, markdown}/{id, name} replaces, {name, markdown} with no id adds, and omission removes a tab, plus the EXACTLY-ONE-of document/sheets constraint. This adds real invocation meaning beyond 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?

States a specific verb and resource ('Writes a new version of a workbook') and immediately scopes it against the run-based path with 'with no run and no charge.' Combined with the versioned-write framing, an agent can distinguish it from commit_workbook/update_workbook without opening a 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 prerequisites and workflow context: send 'base_version — the version you read,' implying read_workbook is the precursor, and 'no run and no charge' signals it is the non-execution alternative. However, it never names a sibling tool or states an explicit when-not condition beyond the refusal cases, so it stops short of full routing 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