check_url_changesUse for repeated research on one public webpage when the agent only needs what changed since its last call. First call stores a baseline; later calls return added/removed text lines. Avoid for authenticated/private pages, binary files, or one-time page reading.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public HTTP(S) webpage URL. Private-network and unsafe targets are rejected. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the burden of disclosing behavior. It effectively reveals the stateful nature: first call stores a baseline, later calls return added/removed text lines. It does not detail persistence duration or exact first-call output, but it covers the core side effect (baseline storage).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose and use cases. Every word contributes value, and the structure flows from when to use to what it does to what to avoid.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter stateful tool with no output schema and no annotations, the description provides sufficient context: state behavior, return contents, and exclusions. It does not explain baseline expiration or first-call return behavior, but given the tool's simplicity, it is nearly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The only parameter, url, is fully described in the schema (public HTTP(S), private/unsafe rejected). The description adds that the same URL is reused across calls, but this is a usage nuance rather than new parameter semantics. With 100% schema coverage, a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the tool's function: tracking changes on a public webpage across repeated calls, with a baseline on first call and added/removed text lines on subsequent calls. It distinguishes itself from siblings like 'check_mcp_surface_changes' by focusing on webpage content rather than MCP surface.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use (repeated research on a single public webpage needing only changes) and when to avoid (authenticated/private pages, binary files, one-time reading). However, it does not name specific alternative tools, so it falls short of the full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool serves a clearly distinct purpose: buying prepaid API calls, monitoring MCP server tool catalogs, and monitoring webpage changes. No overlap or ambiguity exists among them.
All tool names follow a consistent verb_noun snake_case pattern: buy_ and check_ prefixes with descriptive objects. This makes the set predictable and easy to navigate.
With only 3 tools, the set is small but appropriate for a focused utility centered on purchasing ChangePacket calls and checking changes in two specific contexts. It avoids bloat while covering the core actions.
The domain appears to be ChangePacket's change-detection service. The purchase mechanism and the two change-checking tools cover the primary workflows, though a tool for viewing usage history or canceling calls might round it out.