Local MCP

Web Find

web_find

Read-only

Finds elements on the current page of a web session so you can decide what to click or type into. query is a CSS selector OR visible text to match. Returns up to 30 matches with tag/text/name/type/href — never a silent empty.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes	A CSS selector (e.g. 'input[name=q]') or visible text (e.g. 'Sign in').
`session`	No	Session name (default 'default').

Output Schema

TableJSON Schema

Name	Required	Description
`count`	No	Number of matching elements (max 30 returned).
`query`	No
`matches`	No	Matched elements with tag/text/name/type/href.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 11, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "count": {
+      "description": "Number of matching elements (max 30 returned).",
+      "type": "integer"
+    },
+    "matches": {
+      "description": "Matched elements with tag/text/name/type/href.",
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "query": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedJul 11, 2026

TDQS

A4.2/5.0

Behavior4/5

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

While readOnlyHint=true and destructiveHint=false already signal a non-destructive read, the description adds meaningful behavior beyond annotations: it caps results at 30, lists returned attributes, and explicitly promises 'never a silent empty.' This helps an agent know what to expect.

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 tight sentences front-load the action and purpose, then cover query format, result count, and the no-silent-empty guarantee. Every clause earns its place with no fluff.

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 simple read-only finder with full schema coverage and an output schema, the description covers what an agent needs: what it finds, how to query, what comes back, and the empty-behavior guarantee. It could add explicit guidance on choosing it over web_read/ui_find_element, but nothing critical is missing.

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?

The schema already documents both parameters with 100% coverage and the same CSS-or-text semantics, so the description adds little beyond restating the query format. Baseline 3 is appropriate; no parameter information is missing, but no new meaning is added.

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?

The description states a specific action ('finds elements') on a specific resource ('current page of a web session') and the intent ('decide what to click or type into'). This is distinct from sibling tools like web_read or web_extract and from ui_find_element by anchoring to a web session.

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?

It clearly implies when to use the tool: before acting on the page, to locate targets for clicking or typing. It does not explicitly name alternatives or say when not to use it, so it falls short of a 5, but the intended context is unmistakable.

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

All Local MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.