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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is edge-case semantics — inclusive start vs exclusive end, rejected tz='local', and the split_periods_by_zone / series_ended_by_zone output channels. That is genuine non-obvious behavior, though nothing is said about result size, limits, or cost of comparing many zones at once.

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 purpose sentence followed by dense, backtick-anchored field names that are easy to scan; nearly every clause carries operational meaning. The parenthetical GB day-ahead-after-2020-12-31 example is a bit of an in-joke but still illustrates the series_ended_by_zone case, so it 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?

An output schema exists, so return values need not be spelled out, and the description covers the trickiest result channels well. However, for a 7-parameter, 4-required comparison tool with zero schema coverage, leaving `aggregation` and `endpoint` undescribed is a real completeness gap that could produce wrong comparisons.

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 0%, so the description carries the full burden, and it only partially delivers: start/end, tz and filters get real semantic detail, but `zones`, `endpoint` and especially `aggregation` (default 'daily') are never explained — aggregation silently changes the shape of every comparison. Coverage of roughly four of seven parameters keeps this at a minimum-viable 3.

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 first line gives a specific verb and resource plus scope: 'Compare one endpoint across multiple zones.' That distinguishes it from the single-series sibling get_series, which is explicitly cross-referenced for filter semantics. It stops short of a full contrast statement naming when get_series is the right call instead.

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?

Concrete guidance is present: tz='local' is rejected and an explicit IANA tz is required for wall-clock alignment, filters are scoped to every zone, and an empty `[]` under series_ended_by_zone must not be read as 'no data yet'. What's missing is an explicit when-to-use-this-instead-of-get_series rule, so the agent must infer the split from the 'see get_series' pointer.

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