FileForge

Overview Schema Source Related Servers Discussions Admin

fileforge_perf_action

Run a Core Web Vitals performance audit on a single page URL across desktop and mobile viewports. Use it to check page speed, store the result, and avoid changing the site.

Instructions

Run a performance audit on a URL across viewports and return Core Web Vitals. Use this for a performance check of one page. Use fileforge_devtools_action for raw session data and fileforge_audit_action for SEO, content and security. Loads the URL in its own tab, closes it afterward, and stores the result by default. It doesn't change the site. Needs the extension.

Input Schema

Name	Required	Description	Default
`url`	Yes	Page URL to audit.
`store`	No	Save the result in ~/.fileforge and return a ref.
`action`	Yes	What to do. Required parameters are in brackets. audit (url): Run a performance audit (Core Web Vitals) across viewports.
`project`	No	Project name that groups stored results.	default
`settleMs`	No	Milliseconds to wait after load before capturing.
`timeoutMs`	No	Time limit in milliseconds.
`viewports`	No	Viewport presets to use, such as "desktop" or "mobile".
`networkIdleMs`	No	Quiet network period that counts as idle, in milliseconds.
`includeScreenshot`	No	Include a screenshot.
`networkIdleTimeoutMs`	No	Longest wait for network idle, in milliseconds.

Output Schema

Name	Required	Description
`ok`	Yes	False if the action failed or a check did not pass.
`ref`	No	Stored result ID, for fileforge_result_action.
`data`	No	The result. Its shape depends on the action.
`meta`	No	Tool, action and context.
`error`	No	Failure code and message.
`warnings`	No	Notes about a call that still ran.

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedv0.3.0Nov 5, 2026

changedInput schema / properties / action / description

Previous value: -"The performance action to perform."New value: +"What to do. Required parameters are in brackets. audit (url): Run a performance audit (Core Web Vitals) across viewports."

addedInput schema / properties / includeScreenshot / description
```
Added value: +"Include a screenshot."
```

addedInput schema / properties / networkIdleMs / description

Added value: +"Quiet network period that counts as idle, in milliseconds."

addedInput schema / properties / networkIdleTimeoutMs / description
```
Added value: +"Longest wait for network idle, in milliseconds."
```

addedInput schema / properties / project / description

Added value: +"Project name that groups stored results."

addedInput schema / properties / settleMs / description

Added value: +"Milliseconds to wait after load before capturing."

addedInput schema / properties / store / description

Added value: +"Save the result in ~/.fileforge and return a ref."

addedInput schema / properties / timeoutMs / description
```
Added value: +"Time limit in milliseconds."
```
addedInput schema / properties / url / description
```
Added value: +"Page URL to audit."
```

addedInput schema / properties / viewports / description

Added value: +"Viewport presets to use, such as \"desktop\" or \"mobile\"."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "description": "query_* actions return their modules as extra top-level fields.",
+  "properties": {
+    "data": {
+      "description": "The result. Its shape depends on the action."
+    },
+    "error": {
+      "description": "Failure code and message."
+    },
+    "meta": {
+      "description": "Tool, action and context."
+    },
+    "ok": {
+      "description": "False if the action failed or a check did not pass.",
+      "type": "boolean"
+    },
+    "ref": {
+      "description": "Stored result ID, for fileforge_result_action."
+    },
+    "warnings": {
+      "description": "Notes about a call that still ran."
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}

First observedv0.2.1Nov 5, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Adds substantial behavior beyond the annotations: it opens the URL in its own tab and closes it afterward, stores the result by default, and requires the extension to be installed. The 'doesn't change the site' line usefully scopes the mutation implied by readOnlyHint=false (writing to ~/.fileforge), so it is consistent rather than contradictory. It stops short of noting runtime/permission constraints, which is why this is a 4 and not a 5.

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?

Five short sentences, front-loaded with what the tool does, then routing to siblings, then side effects and prerequisites. Nothing is repeated and nothing could be dropped without losing signal.

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

Completeness5/5

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

For a 10-parameter tool with an output schema and full schema coverage, the description covers the remaining unknowns an agent needs: sibling disambiguation, the tab lifecycle side effect, default persistence, and the extension prerequisite. Return values need not be described since an output schema exists.

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 100%, so the schema already documents url, store, project, viewports, settleMs, timeoutMs and the rest. The description only reinforces the viewport dimension and the Core Web Vitals output; it adds no tuning guidance for settleMs, networkIdleMs or timeoutMs. Baseline 3 applies.

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?

States a specific verb and resource ('Run a performance audit on a URL across viewports') and names the concrete output ('Core Web Vitals'). It also explicitly separates itself from fileforge_devtools_action and fileforge_audit_action, so an agent can choose it without opening either schema.

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

Usage Guidelines5/5

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

Gives a positive condition ('Use this for a performance check of one page') and names two alternatives with the exact conditions that select them: raw session data vs SEO/content/security. There is no ambiguity about when this tool is the right choice.

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