FileForge

Overview Schema Source Related Servers Discussions Admin

fileforge_search_action

Read-onlyIdempotent

Search local saved pages, stored results, notes, browser history, and bookmarks by text, or narrow the search to a single source.

Instructions

Search local data by text: saved pages, stored results, notes, browser history and bookmarks. Use all to search everything, or narrow it to one source. Use fileforge_memory_action to compare page visits and fileforge_scrape_action to read a live page. History and bookmarks need the extension.

Input Schema

Name	Required	Description
`ref`	No	Ref of a stored result.
`limit`	No	Maximum items to return.
`query`	No	Search text.
`action`	Yes	What to do. Required parameters are in brackets. all (query): Search across pages, notes, history, and bookmarks. page (query): Search within the text of a specific page result. notes (query): Search saved notes. history (query): Search browser history. bookmarks (query): Search browser bookmarks.

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.

Changed5 schema fields changedv0.3.0Nov 5, 2026

changedInput schema / properties / action / description

Previous value: -"The action to perform. Available actions: all: Search across pages, notes, history, and bookmarks. page: Search within the text of a specific page result. notes: Search saved notes. history: Search browser history. bookmarks: Search browser bookmarks."New value: +"What to do. Required parameters are in brackets. all (query): Search across pages, notes, history, and bookmarks. page (query): Search within the text of a specific page result. notes (query): Search saved notes. history (query): Search browser history. bookmarks (query): Search browser bookmarks."

addedInput schema / properties / limit / description
```
Added value: +"Maximum items to return."
```
addedInput schema / properties / query / description
```
Added value: +"Search text."
```
addedInput schema / properties / ref / description
```
Added value: +"Ref of a stored result."
```

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

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real context beyond them: the data is local-only, and history/bookmarks results require the browser extension to be installed. It does not discuss result ordering or paging behavior, but the output schema carries return shape.

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

Conciseness4/5

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

Four short sentences, front-loaded with purpose, then selection, then alternatives, then the extension caveat. Efficient overall, though the source list in sentence one partially overlaps with the "all" explanation in sentence two.

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 read-only search tool with full annotation coverage and an output schema, the description covers purpose, action selection, alternatives, and the extension prerequisite. The only minor gap is that ref-based narrowing (action=page) and the limit default are left entirely to the schema, which is acceptable but not exhaustive.

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% and the action enum already spells out each value with its required parameters in brackets, so the schema does the heavy lifting. The description reinforces the action semantics with the "all vs one source" framing, but it does not mention the ref parameter at all, and "stored results" in its source list has no matching enum value. Baseline 3 is appropriate.

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?

Opens with a specific verb and resource ("Search local data by text") and enumerates the corpora covered: saved pages, stored results, notes, browser history, bookmarks. It explicitly names the siblings it is not (fileforge_memory_action, fileforge_scrape_action), so an agent can route without opening another 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 direct selection rule ("Use all to search everything, or narrow it to one source") plus two explicit alternatives with their conditions: memory_action for comparing page visits, scrape_action for reading a live page. It also states a prerequisite (history and bookmarks need the extension), which is the kind of when-not guidance most definitions omit.

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