Agent Paywire library

List changes after a date

changes_since

Read-onlyIdempotent

List every record whose verified_at is later than cursor (exclusive) across library sources, articles, datasets, bots and support notes, with kind, id, title, url and verified_at. There is no limit or paging, so an old cursor can return the whole catalog (over 100 entries, about 43 KB); store the latest verified_at you saw and pass it next time. Non-library ids are prefixed (article:, dataset:, bot:, support:); remove the prefix before calling get_article, get_dataset, or get_bot. Library ids have no prefix and go to get_source. Use search with updated_since to filter library sources only, and latest_sources for a short newest-first list. A cursor that is not YYYY-MM-DD returns an isError result. Free, no auth.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`cursor`	Yes	Date as YYYY-MM-DD, e.g. 2026-10-19. Records with verified_at strictly later are returned; today's date usually returns 0 rows. Other formats are rejected.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`count`	Yes
`cursor`	Yes
`entries`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 20, 2026

changedInput schema / properties / cursor / description

Previous value: -"YYYY-MM-DD. Example: 2026-10-19. Records with a later verified_at are returned."New value: +"Date as YYYY-MM-DD, e.g. 2026-10-19. Records with verified_at strictly later are returned; today's date usually returns 0 rows. Other formats are rejected."

Changed2 schema fields changedOct 20, 2026

changedInput schema / properties / cursor / description

Previous value: -"YYYY-MM-DD. Records with a later verified_at are returned."New value: +"YYYY-MM-DD. Example: 2026-10-19. Records with a later verified_at are returned."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "count": {
+      "type": "integer"
+    },
+    "cursor": {
+      "type": "string"
+    },
+    "entries": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "kind": {
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          },
+          "verified_at": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "kind",
+          "title",
+          "verified_at"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "cursor",
+    "count",
+    "entries"
+  ],
+  "type": "object"
+}

First observedOct 20, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already cover read-only/idempotent/non-destructive, so the description focuses on what they cannot express: there is no limit or paging, an old cursor can return the whole catalog (~100 entries, ~43 KB), and the caller should persist the newest verified_at as the next cursor. It also discloses that a malformed cursor yields an isError result and that the tool is free with no auth.

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?

One dense paragraph, but front-loaded with the core operation and then layered with operational caveats (no paging, size estimate, cursor chaining, id prefixes, alternatives, error mode). Every sentence carries actionable information and nothing is filler.

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-value explanation is unnecessary, and the description still covers the operational facts an agent needs: no pagination, id-prefix routing to sibling get_* tools, cursor chaining, and error behavior. Nothing needed to invoke this correctly 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 the single cursor parameter is already fully documented in the schema, including the YYYY-MM-DD format and the 'strictly later' semantics. The description's cursor notes (exclusivity, invalid-format rejection) largely restate the schema, so the 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 ('List every record whose verified_at is later than cursor (exclusive)') plus the exact scope (library sources, articles, datasets, bots, support notes) and returned fields. It is unmistakably distinct from search, latest_sources, and the get_* siblings.

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?

Explicitly routes the agent: 'Use search with updated_since to filter library sources only, and latest_sources for a short newest-first list.' It also tells the agent how to interpret returned ids (strip the article:/dataset:/bot:/support: prefix before calling the corresponding get_* tool, unprefixed ids go to get_source).

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

All Agent Paywire library 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.

Resources

Need Help?