Skip to main content
Glama
Sign In
yof

yof

Official
by yof-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Findings from your yof account

yof_findings
Read-onlyIdempotent

List open findings from your yof.io account to see known issues on proven live apps and connected GitHub repositories. Use returned ids with the fix prompt; this does not scan local code.

Instructions

List open findings stored in your yof.io account: problems yof found on your proven apps' live sites and connected GitHub repositories. Use it to see what yof.io already knows; it does not scan this computer (use yof_check or yof_check_diff for that), and yof_fix_prompt takes a finding id from here. Needs YOF_API_KEY; sends only these arguments to yof.io and returns results from yof's latest checks, most recently seen first. Returns findings (id, app, rule, title, severity, where, redacted value, first and last seen) and next; an empty list means no open findings, and apps not proven yours are left out.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "yof_findings"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoAt most this many findings, 1 to 200. Default 50.
app_idNoOne app's id, to list only that app. Default: every proven app in the account.
severityNoOnly this urgency: fix_now (fix today), fix_week, nice or info. Default: all.

Output Schema

NameRequiredDescriptionDefault
nextYesWhat to do next.
noteNoPresent when some apps are not proven yours.
findingsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.3.2
    • changedInput schema / properties / app_id / description
      Previous value: -"One app's id (default: all your apps)."New value: +"One app's id, to list only that app. Default: every proven app in the account."
    • changedInput schema / properties / limit / description
      Previous value: -"At most this many (default 50)."New value: +"At most this many findings, 1 to 200. Default 50."
    • changedInput schema / properties / severity / description
      Previous value: -"Only this urgency."New value: +"Only this urgency: fix_now (fix today), fix_week, nice or info. Default: all."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "findings": {
+      "items": {
+        "properties": {
+          "app": {
+            "description": "The app's address.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "app_id": {
+            "description": "The app's id.",
+            "type": "string"
+          },
+          "first_seen": {
+            "description": "ISO time.",
+            "type": "string"
+          },
+          "id": {
+            "description": "Finding id, for yof_fix_prompt.",
+            "type": "string"
+          },
+          "kind": {
+            "description": "Kind of check that found it.",
+            "type": "string"
+          },
+          "last_seen": {
+            "description": "ISO time.",
+            "type": "string"
+          },
+          "rule": {
+            "description": "Rule id.",
+            "type": "string"
+          },
+          "severity": {
+            "description": "Urgency.",
+            "type": "string"
+          },
+          "title": {
+            "description": "Readable rule name.",
+            "type": "string"
+          },
+          "value": {
+            "description": "Prefix plus REDACTED.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "where": {
+            "description": "File, path or URL, and line.",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "next": {
+      "description": "What to do next.",
+      "type": "string"
+    },
+    "note": {
+      "description": "Present when some apps are not proven yours.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "findings",
+    "next"
+  ],
+  "type": "object"
+}
  2. First observedv0.3.1

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, openWorld, non-destructive), it discloses the auth requirement (YOF_API_KEY), data egress ("sends only these arguments to yof.io"), freshness (results from yof's latest checks), ordering ("most recently seen first"), and an exclusion rule (apps not proven yours are left out). That is unusually rich context that annotations cannot express.

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?

Front-loaded with purpose, then alternatives, then auth/behavior, then return shape — a sensible order with no filler sentences. It is dense and runs long in a single block, which slightly hurts scannability, but every clause carries information an agent would otherwise have to guess.

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?

Even though an output schema exists, the description still summarizes the return fields and the empty-list semantics ("an empty list means no open findings"), which is the one case a schema cannot convey. Auth, scope, ordering and sibling handoffs are all covered, so nothing needed for a correct call 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?

Schema coverage is 100% and each parameter already carries its own description, bounds and enum values, so the description does not need to restate them. It only adds the implicit scoping claim that the argument set is the complete request payload, which is marginal added meaning over the schema.

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 — "List open findings stored in your yof.io account" — and immediately defines what a finding is ("problems yof found on your proven apps' live sites and connected GitHub repositories"). That definition alone separates it from yof_check, yof_explain and yof_verify without needing their schemas.

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 an explicit when-to-use ("see what yof.io already knows"), an explicit when-not with named alternatives ("it does not scan this computer (use yof_check or yof_check_diff for that)"), and a downstream handoff note ("yof_fix_prompt takes a finding id from here"). Routing is fully determined from the description.

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

Deploy Server

Other Tools