Skip to main content
Glama

reflex_verify

Confirms expected text appears on the current page or desktop after an action, returning success, found status, and evidence so agents can verify changes.

Instructions

Verify expected text is present on the current page (or desktop if no page). Use after every changing action. Returns success, found, and the evidence window.

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": {
      "expected": "<expected>"
    },
    "name": "reflex_verify"
  }
}

Input Schema

NameRequiredDescriptionDefault
expectedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations present, the description carries the full burden and does disclose the desktop fallback and the return payload shape ('success, found, and the evidence window'). However, it never states what happens on failure (throws vs. returns found:false), whether it waits, polls, or has a timeout, or whether the evidence window is an image, DOM snippet, or text excerpt — meaningful gaps for a verification tool an agent must branch on.

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

Conciseness5/5

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

Two tightly packed sentences: the core action and scope come first, the timing directive second, and the return contract last. No filler, no restatement of the tool name, nothing that could be cut without losing information.

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 one-parameter tool with no output schema, the description covers purpose, invocation timing, scope fallback, and the shape of the return value — enough for an agent to call it correctly. The remaining gap is failure and matching semantics, which matter because the agent must decide how to react to a negative result.

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

Parameters3/5

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

Schema description coverage is 0% and the single parameter 'expected' is undocumented in the schema, so the description must compensate; it does so partially by framing 'expected' as the text that must be 'present'. It adds no matching semantics — no indication of substring vs. exact vs. regex, case sensitivity, or multi-line handling — leaving the most consequential ambiguity for this tool unaddressed.

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 object ('Verify expected text is present') plus a scope qualifier ('current page (or desktop if no page)'), so an agent knows exactly what is being checked and against which surface. It does not name or contrast a sibling tool, but the sibling list is dominated by unrelated body_* utilities, so differentiation is less critical here.

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?

The imperative 'Use after every changing action' is an explicit, actionable when-to-use directive that tells the agent to call this as a post-mutation checkpoint. There is no what-not-to-do guidance (e.g., don't use for structured assertions or before the page settles), which is why this is not a 5.

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