teardown-observe

Overview Schema Source Related Servers Discussions Admin

probe_web_field

Test a single form field to map equivalence classes, length boundaries, and per-class outcomes, returning named actions and folded claims for flow learning.

Instructions

Probe one form field (web, Android or desktop UI): equivalence classes for its kind (text/email/password/number or custom classes), a length-boundary search, per-class outcomes and folded claims. prefix = named actions that reach the form; submit = the named action that submits it. Boundary classes become named actions you can add to learn_flow's alphabet. When accepted values change the outcome (computed results), say what acceptance looks like: accepted_if = {subset: {...}} and/or {text_contains: '...'}. Number fields skip the length search (their limits are ranges). Without submit, the outcome is read right after typing (live previews, totals, counters).

Input Schema

Name	Required	Default
`kind`	No	text
`name`	Yes
`role`	Yes
`valid`	No
`prefix`	Yes
`submit`	No
`classes`	No
`feature`	Yes
`boundary`	No
`accepted_if`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.2.0Oct 24, 2026

addedInput schema / properties / submit / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / submit / default
```
Added value: +null
```
removedInput schema / properties / submit / type
```
Removed value: -"string"
```

changedInput schema / required

Previous value: -[
-  "feature",
-  "prefix",
-  "role",
-  "name",
-  "submit"
-]New value: +[
+  "feature",
+  "prefix",
+  "role",
+  "name"
+]

First observedv0.1.0Oct 23, 2026

TDQS

B3/5.0

Behavior3/5

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

With no annotations, the description carries the full burden and does disclose meaningful mechanics: boundary classes become named actions, submit controls whether an action is invoked, and number fields skip length probing. It does not disclose whether submitted forms can mutate state, what permissions are required, or any safety/rate-limit considerations, which is a notable omission for a UI-probing tool that may submit forms.

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

Conciseness3/5

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

The description is compact and front-loads the core operation, but it is dense with domain jargon such as 'folded claims' and 'learn_flow's alphabet,' making it harder to parse. The content is not bloated, but the structure could be clearer for an agent unfamiliar with the project vocabulary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex 10-parameter tool with no annotations and no schema descriptions, so the description needs to be more complete. It covers several key parameters and behaviors, but required parameters and safety implications of submitting forms remain unexplained; the output schema does at least cover return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 10 parameters, so the description must compensate. It explains `prefix`, `submit`, `classes`, `kind`, and `accepted_if`, but leaves required parameters like `feature`, `role`, and `name` plus `valid` and `boundary` unexplained, forcing the agent to guess their meaning.

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?

The description gives a specific verb and resource: 'Probe one form field (web, Android or desktop UI)' and states the core outputs (equivalence classes, boundary search, per-class outcomes). It is clear what the tool does, though it does not explicitly differentiate itself from siblings such as probe_cli or discover_ui.

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?

It provides useful operational conditionals: number fields skip the length search, and without a `submit` action the outcome is read right after typing. However, it never states when to choose this tool over alternatives like probe_cli or discover_ui, so usage is implied rather than explicitly guided.

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