Zone brief (current state in context)

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered and the description carries a lower burden. It adds useful non-obvious behavior: data is 'strictly at-or-before now', the context window is the zone's own last ~30 days, and crucially, the free sample-mode behavior (truncated history at 50 rows, brief returning one context block, results clearly marked). Auth requirements (Bearer header vs X-PAYMENT) are also disclosed. No contradiction with 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?

The description is long but every sentence earns its place: purpose is front-loaded, then usage guidance, then auth/sample-mode details. The auth portion is dense and could arguably be split out, but it is actionable and not redundant. For the complexity of the tool it is appropriately sized and not padded.

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-value burden, and it does so in solid detail: it names the metrics, the ranking statistics (percentile, vs-median %, min/max, sample count, data window), the per-metric 24h trend, the generation mix (scoped to where published), and the summary sentence. The sample-mode truncation is explained. Minor gaps — the phrase 'brief returns one context block' is vague about what a truncated brief looks like — but coverage is strong for a composite 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 description coverage is 100%, so the schema already documents both parameters thoroughly — zone's enum with regional groupings and api_key's purpose. The description adds marginal value by weaving the api_key story into the broader auth section (header vs argument vs sample mode), but it does not substantially enrich parameter semantics beyond what the schema states. Baseline 3 is appropriate.

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 opens with a specific, weighted verb-noun pair — 'Composite, interpretation-ready snapshot of one zone' — and enumerates the exact contents (price/demand/carbon intensity ranked against the zone's last ~30 days, 24h trend, generation mix, one-sentence summary). This clearly distinguishes it from siblings like get_latest (raw values) and get_history (historical series), and the title 'current state in context' reinforces the differentiation.

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 description gives explicit, quotable use cases: 'Best tool for questions like "is electricity cheap/clean in X right now" or "is this a good time to run a flexible workload"', which tells an agent when to reach for this tool. It also implies contrast with raw-data paths ('A raw price means little without this context'), implying get_latest for bare values. It does not name sibling alternatives explicitly or spell out when-not-to-use, but the context is clear enough for routing.

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