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

Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely useful context beyond them — the underlying NSRDB typical-year weather file, an explicit accuracy caveat, and the payment model ($0.002 USDC per successful call via x402 on Base/Solana/Arc, with failed calls not charged). Cost and data-provenance details like this are exactly what annotations cannot express. Rate limits and error behavior are not covered, keeping it from a 5.

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 sentences, front-loaded with identity and outputs, then a compact clause for data source, caveat, and price. Every clause carries distinct information and nothing is repeated from the schema or annotations.

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 an output schema present, the description needn't explain return values, and it already lists the key outputs anyway. Annotations cover the read-only posture, the schema fully documents all five parameters, and the description supplies the remaining decision-relevant facts: data source, accuracy caveat, and pay-per-call cost. Nothing an agent needs to decide or call correctly is missing.

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% and every parameter (lat, lon, tilt, azimuth, capacityKw) already documents its range and defaults. The description adds only "at a latitude and longitude", which is no more than the required-field statement in the schema. Per the baseline rule, a 3 is correct.

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?

Names a specific upstream model and version (NLR/NREL PVWatts v8) applied to a specific resource and scope (grid-connected PV system at a lat/lon), then enumerates the exact outputs: annual AC energy, capacity factor, annual solar radiation, monthly AC energy. That is far more than a restated name. It never distinguishes itself from the closest sibling, energy_global_solar_atlas_pv, which also deals with site-level solar resource, so it stops short of a 5.

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?

"Grid-connected PV system" and "this is an estimate, not a yield guarantee" implicitly scope the tool to pre-feasibility yield estimation, but there is no explicit when-to-use or when-not language and no routing to the alternative solar tools. An agent must infer the choice from domain knowledge.

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