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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description adds real context beyond them: 90-day history, newest-first ordering, 1 credit per call, and an unauthenticated preview capped at 5 rows and 20 calls/day. It stops short of describing pagination interaction with the preview cap, but the operational constraints are unusually well disclosed.

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?

Front-loaded with what the tool returns before the operational details, and every clause carries information (cost, limits, filter syntax). The inline source enumeration is long but necessary for disambiguation, so it earns its space.

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?

With no output schema and low schema coverage, the description supplies the return semantics (delta rows, newest first) plus cost and rate limits. It is close to self-sufficient for a 6-param tool, with only per-parameter details for page/per_page/change left to the schema enums.

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 coverage is only 17%, so the description must carry the load, and it does for the hardest parameter: `filter` is explained as the source's own query params applied to the changed record, with a worked example and a pointer to list_sources supported_params. `source` values and the 90-day `since` window are implied, but page/per_page/change remain undocumented beyond their enums.

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?

States a specific verb and resource: 'Rows added, removed or changed between daily refreshes of a register dataset', then enumerates the exact datasets. It is immediately distinguishable from the sibling query_* tools, which read a whole register rather than a delta.

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?

Explicitly instructs 'Poll this instead of re-reading a whole register', naming the alternative behavior (full-register query tools) and the condition that selects this tool. The filter example shows a concrete polling use case, removing nearly all inference.

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