Skip to main content
Glama
Sign In

hedwigai

by com.hedwigai
OverviewDiscussionsAdmin

Link a workbook to a file in Drive or Dropbox

link_workbook
DestructiveIdempotent

Makes a file in this account's Google Drive or Dropbox the document of record for a workbook. The file is brought in now — an empty workbook is seeded from it, and one with versions gets its content as the next version — and from then on:

  • every run and every checkout_workbook brings the file in first, so work starts from what is in the drive, including an edit made in Excel or Word since;

  • every new version is written back over the file IN PLACE (the same Drive file, its sharing and revision history kept).

An Excel workbook (.xlsx, .xlsm) is edited as the spreadsheet itself: a run gets it as draft.xlsx and the xlsx program, and the file goes back with its formulas, formats and every untouched sheet as they were. A Word document (.docx) is edited as markdown and written back into its own package, so its styles, headers and footers stay.

A file changed in the drive while a run was working is NOT overwritten; the workbook's link.last_error says so, and the next pull brings that change in.

Input Schema

NameRequiredDescriptionDefault
pathYesThe file on a mount, as the shell names it: `googledrive/Sites/339 15th St/Rent Builder.xlsx` or `dropbox/memo.docx`.
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

A4.5/5.0
Behavior5/5

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

Annotations only flag destructiveHint/openWorldHint/idempotentHint; the description goes substantially beyond them. It discloses exactly what is destroyed and what is preserved: every new version overwrites the Drive file IN PLACE while keeping its sharing and revision history, formulas/formats/untouched sheets survive for xlsx, styles/headers/footers survive for docx, and an edit made in the drive mid-run is NOT overwritten but surfaced in link.last_error. That is precisely the mutation-risk context an agent needs.

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, then two bullets covering the pull-side and push-side contract, then format-specific behavior, then the conflict case. Dense but well organized; the xlsx/docx paragraph is the longest and slightly over-detailed, but it earns its place by changing how an agent prepares a run.

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, long-lived binding operation with no output schema, this covers seeding behavior, ongoing sync in both directions, format preservation, and conflict/error signaling via link.last_error. Remaining gaps are modest: what happens if the path is missing or the wrong type, whether an existing link is replaced, and whether auth/scopes are needed for the target drive.

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 schema baseline is 3, but the description adds real semantic constraints the schema does not: valid path targets are .xlsx/.xlsm (edited as a real spreadsheet, surfaced to a run as draft.xlsx with the xlsx program) and .docx (edited as markdown). That tells the agent which files this tool can meaningfully accept. The analytics-only context/llm_model parameters are left to the schema, which is fine.

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: makes a Drive/Dropbox file the 'document of record' for a workbook. That framing distinguishes it from siblings like add_attachment (attaches, does not bind) and unlink_workbook (the inverse), so an agent can pick it without opening another 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?

Explains the effect on an empty workbook (seeded) versus one with versions (content becomes next version), and states the ongoing contract with checkout_workbook and every run. It gives clear trigger context, but it never explicitly names when to prefer this over alternatives such as add_attachment, unlink_workbook, or pull_workbook, and gives no when-not/exclusion 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