whats_changed_todayThe daily "what changed on the internet" digest: a ranked top-20 of the most significant DNS, TLS, WHOIS, and infrastructure changes observed across the tracked catalog in the last 24 hours. Public and keyless. The complete change wire with sync cursors is the keyed /v1/changes endpoint.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only mark readOnlyHint, and the description adds useful behavioral context: it's public/keyless, returns a ranked top-20, covers the last 24 hours, and is a digest rather than the full change feed. This goes beyond bare read-only semantics without contradicting annotations.
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 pack a high information density: content type, ranking, time window, security context, and a reference to the fuller endpoint. No fluff.
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 parameterless, read-only digest tool with no output schema, the description covers what, when, and why, and even mentions the alternative for more complete data. This is fully adequate.
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 input schema has zero parameters, so the baseline is 4. The description doesn't need to explain parameters since none exist.
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 states this is a daily digest of significant internet infrastructure changes (DNS, TLS, WHOIS) over the last 24 hours, with a ranked top-20 format. This specific verb-plus-resource makes it distinct from sibling tools like lookup_domain or signing_keys.
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?
It notes the tool is 'public and keyless', implying it's the easy-access version, while the complete change wire with sync cursors is available via a keyed endpoint. This provides some guidance on when to use this digest versus the fuller endpoint, though it doesn't explicitly name alternative tools.
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 has a clearly distinct purpose: aggregate rollup, domain lookup, receipt verification, public keys, and daily digest. No overlap.
Naming patterns are mixed: verb_noun (lookup_domain, resolve_receipt), noun_noun (internet_tape), gerund_noun (signing_keys), and a phrase (whats_changed_today). While readable, they lack a consistent convention.
Five tools are well-suited for the domain intelligence service, covering essential operations without being excessive or insufficient.
The tool surface covers core functionality – aggregate stats, domain lookup, verification, and daily digest – but lacks batch queries or historical trends, which are minor gaps.