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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds valuable context: the data sources (NOAA, EIA), the update cadence ('Updates: daily'), and the nature of the returned score. It does not contradict annotations and provides useful behavioral information beyond the structured fields.

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 dense sentences that front-load the core function ('Returns a 0-100 grid heating-stress score'), followed by use cases and update frequency. No fluff, but the first sentence is long and packs many output fields and methodology details. Efficient but slightly dense.

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 description provides the score range, output field names, data sources, use cases, and update frequency. The optional 'days' parameter is fully documented in the schema. For a read-only tool with one optional parameter, this is nearly complete, though the description does not mention the optional history feature or tier requirement—that's only in the schema.

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?

The input schema has only one optional parameter 'days' with a thorough description covering behavior and tier restrictions, giving 100% schema coverage. The tool description itself does not mention parameters, but the schema fully compensates, so the baseline 3 applies.

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 clearly states the tool returns a 0-100 grid heating-stress score, lists the specific output fields (stress_score, stress_level, hdd_zscore, etc.), and describes the methodology (NOAA heating-degree-days z-scored against a multi-decade baseline, cross-read with EIA commercial electricity retail sales). This is specific and distinguishes it from the many generic adw siblings.

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?

Provides explicit use cases: 'Call when the user asks about cold-snap grid stress, heating demand, winter electricity load, or HDD anomalies, or when timing power procurement, demand-response dispatch, or energy-cost decisions.' However, it does not mention alternatives or when not to use this tool, so it misses the 'when-not' criteria for a 5.

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