compare_sites

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

Annotations only declare readOnlyHint=true, so the description carries the behavioral load and does so richly: data provenance (eGRID location-based vs Green-e market-based, EIA-861 2023), the exact utility-selection fallback chain, the rate_basis escape hatch, and tie semantics (best_* = null with *_tied lists). This is well beyond what the annotation provides.

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 purpose and site scope are front-loaded in the first clause, and the trailing sentences are dense but each clause carries distinct information (rate heuristic, window, annual outputs, tie handling). The heavy nested parenthetical about utility selection is the one place where readability suffers.

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 must explain returns, and it does: per-site metrics, competition ranks by carbon/cost/combined, gap percentages, and best_*/_tied null behavior. An agent has everything needed to call it correctly and interpret the result.

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 baseline is 3; however the description adds real meaning by explaining how $/kWh is derived (full-service first, then public power/IOU/co-op, delivery-only retail choice, else state average) and how duration maps to the cleanest window, which the schema does not convey.

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?

Opens with a specific verb+resource+scope: 'Compare and rank 2-25 candidate US sites (ZIP codes)' and names the decision dimensions (carbon, cost). It is clearly distinguishable from siblings like lookup_batch (single-lookup batch) and cleanest_hours (window only) because it explicitly aggregates ranking output across sites.

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?

States the intended load types (facility, data center, EV/flexible load) and 'in one call' implies the batch-comparison use case, plus it routes rate-sector choice ('use IND for industrial/data-center loads'). It cross-references the lookup utility.primary heuristic for consistency, but gives no explicit when-not or 'use X instead for a single site' alternative.

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