Skip to main content
Glama

do_steps

Execute a known sequence of desktop UI actions in one call, waiting to inspect results until the end. The batch validates up front and aborts before starting if any step cannot finish.

Instructions

Run a short sequence of actions in ONE call and look once at the end. Every separate tool call costs a model round trip of several seconds while the action itself takes milliseconds, so a known sequence -- activate, click, type, press Return, see the result -- belongs here rather than in four calls. Steps run with their own look off; the picture is taken after the last one, or at the step that failed. Use single tools when the next action depends on what the last one revealed. The sequence is validated up front -- a call that cannot finish never starts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
lookNoWhat to show you afterwards. Default "auto": wait for the screen to stop changing, measure how much this action changed, and attach a picture of the affected window only if something did change -- so a click that hit nothing costs no tokens and says so. "window" always attaches it, "screen" uses the whole desktop (slower, 6x the tokens), "region" uses look_at, false skips all of it. Use false for the middle of a sequence you are going to check at the end anyway.auto
stepsYesOrdered actions. Each is {do: verb, ...the same arguments that tool takes}. Verbs: activate(target), click(x,y), move(x,y), drag(from_x,from_y,to_x,to_y), scroll(x,y,dy), type(target,text), key(target,combo), press(path,expect_name), set_text(path,text), wait_for(condition,target,timeout) -- same arguments as the wait_for tool; 'wait' is an alias -- and sleep(ms, 1-60000; prefer a wait_for condition over a guessed duration). A malformed step anywhere refuses the whole call naming that step, and nothing executes. Any step may carry retry: {"attempts": N, "on": [codes]} -- it reruns on those error codes (default: the world-moved set) and reports how many runs it took.
look_atNoRectangle for look:"region", in screen pixels. Object form {x, y, width, height} or array form [x, y, width, height].
settle_max_sNoHow long to wait for the screen to stop changing before looking. Raise it for an app that animates slowly; set it to 0 to capture immediately.
stop_on_errorNoStop at the first failing step. Leave this true unless the steps are genuinely independent.
Install Server

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden. It discloses that steps run with their own look off, the picture is taken after the last step or the failing step, and the sequence is validated up front so a call that cannot finish never starts. This is useful, non-obvious execution behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

The description is front-loaded with the core purpose, then explains the cost rationale, the alternative case, and the up-front validation guarantee. Every sentence contributes and no space is wasted.

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 complex tool with no output schema, the description covers the critical context: when to batch, when not to, how look behaves, and how failures are handled. A formal return description is absent, but the observable outcomes are clearly implied.

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?

Input schema coverage is 100%, and the schema already documents steps, look, look_at, settle_max_s, and stop_on_error in detail. The description adds selection context but does not need to repeat parameter syntax; it correctly leaves parameter semantics to 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?

The first sentence clearly states the tool's purpose: run a short sequence of actions in one call and look once at the end. It also names typical verbs and explicitly contrasts with making four separate calls, making it distinguishable from the single-action sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance: batch known sequences because separate calls cost round trips, and use single tools when the next action depends on what the last one revealed. This directly tells an agent when to choose do_steps versus a sibling.

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

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tristanmuzzu/deskwright'

If you have feedback or need assistance with the MCP directory API, please join our Discord server