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

Despite the light annotations (readOnlyHint/idempotentHint/destructiveHint), the description alone carries the full safety-and-quality burden: it discloses that the $/MWh gas-to-grid metric is WITHDRAWN, explains the data-quality failure with specifics (5.5x divergence across five surfaces, a physically impossible $6.73/MWh for Phoenix stamped 'live'), states that $/MMBtu layers are still returned, and names the status field (gas_to_grid_status) that carries the reason. No annotation is contradicted.

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 is front-loaded in a single crisp sentence, and the withdrawal notice is clearly delimited with a dated marker. The narrative is somewhat verbose — the 5.5x/$6.73/Phoenix backstory could be tightened — but the length is defensible because it justifies why the $/MWh must not be trusted, which is critical safety information for an agent.

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?

For a tool of this complexity (a withdrawn output, data-quality caveats, and a conditional parameter), the description covers nearly everything: returned layers, withdrawn metric, status field, invocation pattern, and the key sibling exclusion. An output schema exists so return-value documentation is not the description's burden. The only real gap is that the fate of the heat_rate_btu_per_kwh parameter after the withdrawal (ignored vs. error) is left slightly ambiguous.

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 per the baseline the schema already documents both market and heat_rate_btu_per_kwh. The description adds modest value by clarifying the $/MMBtu unit context and by explaining that heat-rate scenarios pertain to the withdrawn $/MWh output, but it does not systematically deepen the semantics of either parameter beyond the schema.

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 first sentence names a specific deliverable — behind-the-meter/gas-fired power inputs for a US data-center market (Henry Hub spot, regional basis differential, delivered industrial + electric gas tariff in $/MMBtu, each with source labels) — which is far more specific than the generic title. It also differentiates itself from the sibling set by explicitly carving out what it is NOT (electricity grid fuel mix, handled by get_grid_data).

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 an exact invocation pattern ('Pass market=<slug>' with concrete examples), and states an explicit exclusion with a named alternative: 'Do NOT use for the electricity grid fuel mix (use get_grid_data).' It also gives behavioral guardrails about not quoting cached $/MWh figures or deriving them without disclosure, which is operational guidance an agent can act on.

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