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

Annotations already declare readOnly, non-destructive, closed-world, so the safety profile needs no restating. The description adds genuinely new behavior: newest-first ordering, row-level granularity, before/after values plus move size, and an important caveat that magnitudes carry their own unit and are not comparable across units.

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?

Three sentences, front-loaded with what the tool returns and its ordering, then the use-case framing, then a practical caveat. The unit warning earns its place; the only minor waste is the somewhat florid 'water plant's cubic metres a day are not megawatts' phrasing.

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, the description carries the return-shape burden and does so well: row-level diffs, both sides of the value, delta magnitude, newest-first. It does not describe pagination or what happens when limit is hit, and does not clarify how a 'tracker' change differs from a register change, leaving small gaps for a 3-parameter read tool.

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 100%, so a 3 would be the baseline, but the description adds interpretive meaning the schema lacks: the three source categories (register, mirrored series, tracker) map onto the register enum, and the unit warning explains why filtering to one register matters when comparing magnitudes. The limit parameter is left entirely to the schema.

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 resource and scope: row-level changes across 'an official register, a mirrored series or a tracker' since a date. It is clearly a change-ledger feed, unmistakably distinct from siblings like list_reports or list_briefs, though it never explicitly contrasts itself with any of them.

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 framing 'answers "what moved since I last looked" in one call' implies the use case (incremental change review) but gives no explicit when-not guidance or named alternative such as pulling a full series history via get_series. Usage is inferable rather than stated.

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