Skip to main content
Glama

docs_type

Types text into Google Docs at a human pace, with natural pauses, optional corrected typos, and Markdown formatting, then inserts or replaces content at chosen positions.

Instructions

Type into a Google Doc like a person: one keystroke at a time in the real editor, at a human pace with natural rhythm, pauses between sentences and paragraphs, and occasional typos corrected with Backspace. Same positions as docs_write (append, prepend, replace_document, insert_after/insert_before/replace_text an anchor, replace_section). Markdown headings, lists and quotes are set with Docs' own shortcuts, bold/italic/strikethrough are toggled with Cmd+B/I/Shift+X as you type; links, code and emoji are pasted. Short text finishes before this returns; longer text keeps typing in the background (in Chrome, even if this call ends) — the result gives a job id for docs_typing and an ETA. Speed: 55 wpm types ~275 characters a minute.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
docYesGoogle Docs URL or document id.
wpmNoTyping speed in words per minute (overrides the profile).
modeNoWhere to type. Default append.
seedNoMake the rhythm and typos reproducible.
textNoContent as literal plain text; each line break starts a new paragraph. Use this or markdown.
waitNoWait for the typing to finish before returning. Default: wait only when it takes under 2 minutes.
typosNoMistakes that get corrected: false for none, or a rate per letter (0-0.1, e.g. 0.02 = 2%). Overrides the profile.
anchorNoinsert_after / insert_before / replace_text: exact text already in the document. replace_section: the heading text.
pausesNoScale for thinking pauses between sentences and paragraphs: 0 = none, 1 = natural (default), 2 = a slow, thoughtful writer.
accountNoWhich signed-in Google account to use: an index as in /u/N/ URLs (0 = first account) or an email address. Omit for the browser default. Use this for documents owned by a second (e.g. school) account.
asBlockNoinsert_after / insert_before: type even one paragraph as its own new paragraph instead of inline.
profileNoTyping style: natural (55 wpm, 2% typos), careful (38 wpm, 0.8% typos), fast (85 wpm, 3% typos), steady (60 wpm, no typos). Default natural.
markdownNoContent as markdown. Use this or text.
matchCaseNo
occurrenceNoWhich match of the anchor: 1 = first (default), -1 = last.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so richly: it discloses async behavior (short text returns before completion, long text keeps typing in the background even after the call ends in Chrome), the returned job id for docs_typing and an ETA, and how formatting is applied via Docs shortcuts versus paste. These are exactly the runtime traits an agent cannot get from the schema or annotations.

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 purpose and dense with useful detail, with no wasted sentences. The middle sentence is long and run-on, which slightly hurts readability, but every clause carries behavioral information.

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 15-parameter async tool with no output schema, the description covers the critical missing pieces: the return value (job id + ETA) and background-execution semantics. It stops short of covering failure modes (e.g., anchor-not-found) or permission/account edge cases, but those are largely handled by the schema.

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 93%, so the baseline is 3, but the description adds real meaning: it maps profile to concrete speed (natural ~55 wpm), quantifies it ("55 wpm types ~275 characters a minute"), and explains that typos are corrected with Backspace and that pauses occur between sentences and paragraphs. This goes beyond the per-parameter schema text without fully restating it.

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 ("Type into a Google Doc") and immediately differentiates itself from the sibling docs_write by describing keystroke-by-keystroke human simulation rather than bulk insertion. It even names docs_write to anchor the shared positioning modes, so an agent can distinguish the two without opening either 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 context for when this is appropriate (human-paced, natural rhythm, "like a person") and routes the agent to docs_typing for job tracking, but never states an explicit when-not rule or a crisp choice criterion versus docs_write beyond "same positions." The guidance is clear but leaves the deliberate selection decision partially to inference.

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