Poll for what's changed since a given date/time instead of re-pulling the whole dataset: newly certified records, superseded (old->new) pairs, and reconfirmed records. Underlying sources are re-checked weekly (Sundays, 00:00 UTC).
| Name | Required | Description | Default |
|---|---|---|---|
| since | Yes | ISO 8601 date or datetime | |
| state | No | ||
| topic | No | ||
| subject | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It discloses what kinds of changes are returned, implies incremental polling rather than a full snapshot, and even states the underlying refresh cadence ('re-checked weekly (Sundays, 00:00 UTC)'). It omits pagination and error behavior, but the disclosed behavior meaningfully exceeds a generic 'lists changes' statement.
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 compact sentences with no filler. The primary purpose and usage context are front-loaded, followed by concrete result categories and a useful freshness detail. Every clause earns its place.
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?
The tool has no output schema and no annotations, so the description must carry more weight. It covers the core inputs and result categories, but the three undocumented optional parameters, plus the absence of any mention of result limits, ordering, or pagination, leave notable gaps for a tool that returns a set of changes.
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?
Schema description coverage is only 25%, so the description must compensate for the undocumented parameters. It clarifies the `since` parameter's intended use ('changed since a given date/time') but provides no meaning for `state`, `topic`, or `subject`, leaving three optional parameters functionally unexplained.
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 names a specific operation, 'Poll for what's changed since a given date/time', and a resource ('records'), then enumerates the exact returned categories: newly certified records, superseded pairs, and reconfirmed records. It also contrasts itself with 're-pulling the whole dataset', which helps distinguish it from the sibling lookup/search tools.
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 clearly frames when to use this tool: when you need to detect changes since a timestamp rather than re-fetching everything. It does not explicitly name sibling alternatives or state when NOT to use it, but the context is strong enough to guide an agent's choice.
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.