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

With no annotations, the description must carry the behavioral burden, and it does disclose a lot: the exact metrics computed, the methodology split (location-based eGRID vs market-based residual mix), input bounds (2-25 zips), and the conditional output branch triggered by annual_kwh. It does not disclose failure modes (invalid or non-US ZIPs), data vintage, or latency cost of pulling hourly grid profiles, which are notable gaps for a multi-site batch computation.

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 with the verb, scope and cost/carbon target, then a compact per-site metric list, then the conditional branch and the returned ranks. Three dense sentences with no filler or repetition of the tool name.

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 and no annotations, this description successfully substitutes for the return documentation by enumerating per-site fields and the ranking outputs. It is nearly complete for the call itself; only error handling and data-recency behavior are left unstated.

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 zips, sector, duration and annual_kwh (including the 10 MW example and the COM/IND default). The description restates the same semantics ('for the sector', 'cleanest daily window', 'With annual_kwh...') without adding format, edge-case or default-behavior detail the schema lacks.

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?

States a specific verb+resource+scope: 'Compare and rank 2-25 candidate US sites (ZIP codes) on grid carbon and electricity cost in one call.' It also enumerates exactly what is produced per site (eGRID CO2e, Green-e residual mix, carbon-free %, retail $/kWh, cleanest window) and what ranks are returned, so it is readily distinguishable from point-lookup siblings like electricity_rate or hourly_intensity.

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?

Frames the use case clearly ('for a facility, data center or EV/flexible load') and the 'in one call' phrasing implicitly positions it against making repeated single-site sibling calls. It gives conditional guidance ('With annual_kwh, also annual tCO2e and annual cost'), but never explicitly names an alternative tool or states when NOT to use this bundling approach.

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