Skip to main content
Glama

fill

Type text into a form field using a snapshot ref or CSS selector, firing input and change events as a person would; returns true on success and fails for missing matches or stale refs.

Instructions

Type value into a form field: a ref from snapshot or the first match of a CSS selector (its input and change events fire, as when a person types). Returns true; fails when nothing matches or the ref is stale.

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": {
      "target": "<target>",
      "value": "<value>"
    },
    "name": "fill"
  }
}

Input Schema

NameRequiredDescriptionDefault
valueYesText to put in the field.
targetYesA ref from the last `snapshot`, e.g. `e12`, or a CSS selector, e.g. `#price`, `form input[name=q]`.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.47-alpha
    • removedInput schema / properties / selector
      Removed value: -{
      -  "title": "Selector",
      -  "type": "string"
      -}
    • addedInput schema / properties / target
      Added value: +{
      +  "description": "A ref from the last `snapshot`, e.g. `e12`, or a CSS selector, e.g. `#price`, `form input[name=q]`.",
      +  "title": "Target",
      +  "type": "string"
      +}
    • addedInput schema / properties / value / description
      Added value: +"Text to put in the field."
    • changedInput schema / required
      Previous value: -[
      -  "selector",
      -  "value"
      -]New value: +[
      +  "target",
      +  "value"
      +]
  2. First observedv0.1.46

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that input and change events fire as with human typing, that the return is `true`, and the two failure modes (no match, stale ref). Missing only details like whether the field is cleared first or what happens to existing content.

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?

Two compact sentences, front-loaded with the action and target forms before the return/failure note. The parenthetical is informative rather than filler; nothing 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?

An output schema exists and annotations are absent, so the description's job is behavioral and it covers event firing, return value, and failure conditions. Only minor gaps remain (field-clearing behavior, visibility/disabled-field handling) for a two-parameter mutation tool.

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 a baseline of 3 applies, but the description adds real meaning beyond the schema: it specifies that a CSS selector resolves to the *first* match, and that consistency with the last snapshot is required for refs. That is useful semantics not present in the field descriptions.

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?

States a specific verb ('type') and resource ('form field'), with the accepted target forms enumerated. An agent can distinguish it cleanly from click, evaluate, or read_text without opening the schema, though it never explicitly names those siblings.

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

Usage Guidelines3/5

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

Implies usage via 'a ref from snapshot or the first match of a CSS selector', which gives context for when the tool applies. It does not state when-not to use it or contrast it with a sibling that could also set a field's value (e.g. evaluate).

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