Type text into a field using its ref, and prevent incorrect input by refusing to act when the page has changed since observation.
Type text into one observed field by its ref, refusing a page that moved since that observation.
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | ||
| text | Yes | ||
| page_key | No |
Changes observed during successful MCP inspections.
v0.2.8Input schema / properties / page_keyAdded value: +{
+ "anyOf": [
+ {
+ "items": {},
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Page Key"
+}v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations, the description discloses a concrete failure mode: it refuses to act if the page has changed since the observation. The annotation set is sparse, so this stated refusal behavior is meaningful; other effects of typing are not described, but the main behavioral caveat is present.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, front-loaded with the action and object, with the important refusal behavior placed in a dependent clause. Every word contributes to selection or invocation confidence; there is no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a three-argument browser mutation with no output schema, the description covers the core action and one precondition, but leaves page_key unaddressed and does not state what a successful or refused call returns. It is minimally viable but has clear gaps an agent would have to resolve by trial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides zero descriptions and only the titles 'Ref', 'Text', and 'Page Key', so the description must compensate. The description clarifies 'ref' as the identifier of an observed field and 'text' as what to type, but page_key is left completely unexplained, and no format or limits are given. Coverage is too low for the description to carry the full semantic burden.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action ('Type text') and target ('one observed field by its ref'), which conveys the core purpose. It does not explicitly differentiate from sibling tools such as browser_press or browser_run, but the notion of a ref from observation makes the target unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'observed field by its ref' implies this tool is used after a browser_observe-like step and that a fresh ref is needed, but there is no explicit when or when-not guidance. No alternative tools are named, so an agent must infer the appropriate selection context from the wording alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.