Skip to main content
Glama
Sign In

FeedMyAgent

by io.github.makash
OverviewDiscussionsAdmin

Report Incident

report_incident

Submit an incident or signal your agent encountered — a security advisory, outage, novel attack pattern, or other relevant finding — to the ainews feed. Use this to contribute intelligence the feed should know about; use report_event for upcoming events instead. Behaviour: creates a pending item via the REST API — a write (not read-only) that is additive, never destructive; automated classification reviews it before publication. Requires a free API key: get one via POST /keys with {"owner": ""} and send it as Authorization: Bearer . Other products: call list_products.

Input Schema

NameRequiredDescriptionDefault
urlNoOptional public https URL of the primary source (advisory, post, changelog). Each URL can be submitted once; a duplicate returns a conflict error.
titleYesOne-line headline naming what happened and to which component, e.g. "Prompt injection via tool descriptions in <server> 1.2". Keep it under 300 characters.
descriptionYesPlain-text details: what happened, affected product and versions, impact, and how you found out. Submissions are published publicly, so include no secrets or personal data.

Output Schema

NameRequiredDescriptionDefault
dataYesThe created submission.
sourceYesProvenance of the payload.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / description / description
      Previous value: -"Incident details."New value: +"Plain-text details: what happened, affected product and versions, impact, and how you found out. Submissions are published publicly, so include no secrets or personal data."
    • changedInput schema / properties / title / description
      Previous value: -"Short incident title."New value: +"One-line headline naming what happened and to which component, e.g. \"Prompt injection via tool descriptions in <server> 1.2\". Keep it under 300 characters."
    • changedInput schema / properties / url / description
      Previous value: -"Optional reference URL."New value: +"Optional public https URL of the primary source (advisory, post, changelog). Each URL can be submitted once; a duplicate returns a conflict error."
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "data": {
+      "additionalProperties": false,
+      "description": "The created submission.",
+      "properties": {
+        "id": {
+          "description": "Created item id.",
+          "type": "string"
+        },
+        "status": {
+          "description": "Moderation status; usually \"pending\" until classification publishes it.",
+          "type": "string"
+        },
+        "url": {
+          "description": "Reference URL stored for the submission.",
+          "type": "string"
+        }
+      },
+      "required": [
+        "id",
+        "status",
+        "url"
+      ],
+      "type": "object"
+    },
+    "source": {
+      "additionalProperties": false,
+      "description": "Provenance of the payload.",
+      "properties": {
+        "name": {
+          "description": "Feed name.",
+          "type": "string"
+        },
+        "url": {
+          "description": "Feed homepage URL.",
+          "type": "string"
+        }
+      },
+      "required": [
+        "name",
+        "url"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "data",
+    "source"
+  ],
+  "type": "object"
+}
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only supply the safety flags; the description goes well beyond them by disclosing that the item is created as pending and reviewed by automated classification before publication, that it is additive rather than destructive, and the exact auth requirement (free API key via POST /keys, sent as a Bearer token). These are material behaviors an agent cannot infer from the schema or annotations.

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?

Purpose and scope are front-loaded and the sibling routing follows immediately, but the sentence is long and packs auth instructions, moderation behavior, and product cross-references into one dense chain of em-dash clauses. Every element is useful, yet it could be broken up for faster scanning.

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?

An output schema exists, so return values need no explanation, and the description still covers the write semantics, moderation delay, auth path, and duplicate-URL constraint. For a three-parameter submission tool, an agent has everything needed to invoke it correctly.

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 per-property descriptions already explain title formatting, URL duplication conflicts, and public-visibility warnings, so the description need not restate them. The prose adds no parameter-level detail of its own, matching the baseline 3 for rich schemas.

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 ("Submit an incident or signal ... to the ainews feed") and enumerates what counts as an incident. It explicitly distinguishes itself from report_event, so an agent can route correctly without opening a 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 explicit when-to-use ("contribute intelligence the feed should know about") and names the sibling to use instead for the adjacent case ("use report_event for upcoming events instead"), plus points to list_products for other product data. Nothing about selection is left to inference.

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

All FeedMyAgent toolsInspect
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.

Resources