Skip to main content
Glama
Sign In
agent-bridge

agent-bridge

by avas-app
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

screen.fill

screen_fill

Type text into an app input by testID, label, placeholder, text, or coordinates, and wait for the render. Clears fields, submits, types character by character, or picks a match with index.

Instructions

Type into an input, then wait for the render. target is a string (testID, label, placeholder or text) or an object that must match every key it sets: {testID, label, placeholder, text, at:[x,y], index}. Unknown keys are errors. {at:[x,y]} hits the smallest element covering that point, for icon-only buttons with no label. Several matches: add an index, either in the target or as a trailing {index:n} argument. {submit:true} also submits. "" clears it. {type:true} types one character at a time, waiting for a render after each (for debounced or per-character inputs; "\n" is the Enter key). An input with no value prop gets its native text set; if that cannot be done the reply has a warning.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "screen_fill"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsNoThe tool's arguments, in order (each any JSON value). Leave out for none.
fullNoReturn a result over 32 KB whole instead of a summary of its size and shape.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.2

TDQS

A4/5.0
Behavior4/5

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

No annotations exist, so the description carries the full load and does so well: it discloses that it waits for a render after typing, that unknown keys are errors, that per-character typing waits per keystroke, and that the reply carries a warning if native text cannot be set. It does not discuss failure modes like element-not-found or focus requirements.

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?

Purpose is front-loaded and nearly every clause carries a concrete rule, so there is little filler. It is a dense run-on wall of text without bullets or line breaks, which makes the many distinct directives harder to scan than they need to be.

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 mutation tool with no annotations and no output schema, the definition covers input resolution, matching ambiguity, submission, clearing, and typing cadence — enough to call it correctly. Missing pieces are the reply shape beyond the warning case and any prerequisite about the target screen being active.

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?

Nominal schema coverage is 100%, but the schema only declares a generic ordered args array and a 'full' flag, so the description must define the actual argument DSL — which it does thoroughly (target forms, matching semantics, index, at, submit, type, clearing). The gap is that 'full' is never mentioned and the ordered/positional nature of args is not connected to the DSL described.

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?

Opens with a concrete verb-plus-resource: "Type into an input, then wait for the render." That is unambiguous and distinct from read-only siblings like screen_findText or screen_snapshot. It stops short of naming screen_setValue as the contrasting alternative for setting values, so sibling differentiation is only implicit.

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 real selection guidance inside the tool's own surface: add {index:n} when several elements match, use {at:[x,y]} for icon-only buttons with no label, use {type:true} for debounced or per-character inputs, use "" to clear. It does not say when to reach for this tool versus screen_setValue or screen_press, so the cross-tool routing is left to inference.

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

Deploy Server

Other Tools