Skip to main content
Glama

fill_input

Types text into a page's text, select, date, time, range, or color field—replacing or appending content—and triggers the page's input handlers.

Instructions

Types into a text field, textarea or contenteditable, replacing its content (or after it with append), key by key so the page's handlers run (~1 ms per character); picks the option(s) named; sets a date, time, range or colour input (YYYY-MM-DD, HH:MM, a number, #rrggbb). Fails without typing on disabled, read-only, non-text or unfocusable elements and when the field rejects the text; notes a reformatted value. For several fields at once use fill_form.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "selector": "<selector>",
      "text": "<text>"
    },
    "name": "fill_input"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesText to type, or a `<select>` option's value or label (`<select multiple>`: one per line, exactly those selected).
appendNoType the text at the end of the current content instead of replacing it. Default: false.
tab_idNoDefault: the active tab.
selectorYesCSS selector, 'host >>> inner' (into an open shadow root or same-origin iframe) or snapshot ref (e12).
instance_idNoDefault: 'default'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0-rc.1

TDQS

A4.7/5.0
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: it discloses the key-by-key typing model and its cost (~1 ms per character), the intent (so the page's handlers run), the failure modes, and that a reformatted value is reported back. These are behaviors an agent cannot infer from the schema.

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 no filler sentences; every clause carries information. It is densely packed with parentheticals, which slightly raises parsing cost, but nothing is redundant.

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, coverage is strong: modes, formats, failure conditions, and the sibling alternative are all present. The only gap is that the return/confirmation value is only hinted at ('notes a reformatted value') rather than described.

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 baseline is 3; the description adds real value by giving concrete input formats the schema omits (YYYY-MM-DD, HH:MM, a number, #rrggbb) and by clarifying append works 'at the end of the current content'. It does not elaborate on tab_id or instance_id, which is acceptable given their schema defaults.

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 (types) and precise target set (text field, textarea, contenteditable, <select>, date/time/range/colour inputs), plus the replace-vs-append mode. It also distinguishes itself from fill_form, so an agent can pick between them 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 Guidelines5/5

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

Explicitly routes multi-field work to fill_form, and the failure clause ('fails without typing on disabled, read-only, non-text or unfocusable elements and when the field rejects the text') tells the agent exactly when this tool will not do the job. That is when-to-use, when-not-to-use, and the alternative in two sentences.

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