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

Annotations already mark this as read-only and idempotent, and the description adds substantial behavioral context beyond that: withdrawn and restored index terms, the warning not to compare pre-2026-08-08 figures with current ones, the deliberate omission of gas storage/LNG/firm pipeline capacity, and the instruction to read dcgi_status and gas_to_grid_status instead of assuming both moved together. It also discloses that gas_to_grid $/MWh remains unfixed due to a 5.5x disagreement across five surfaces.

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The description is long, but the length is largely justified by the tool's many caveats, withdrawn fields, and need to distinguish sibling tools. It is front-loaded with the use case and core return object before diving into warnings, and most sentences carry operational value. A small amount of redundancy and all-caps emphasis prevents a perfect score.

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?

Despite the output schema existing, the description goes beyond it to explain important runtime context: null delivered price where tariff data is sparse, per-field data_basis provenance, withdrawn vs restored fields, omitted categories, and how to route different user questions to different sibling tools. For a complex data-fusion tool, this is thoroughly complete and should leave an agent well-equipped to call it correctly.

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 explains both state and region parameters. The description reinforces that region accepts a US state code or name with examples like 'TX', 'Texas', and 'Virginia', which is helpful but not materially beyond the schema. This is the appropriate baseline score given the high schema coverage.

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 opens with a specific trigger condition ('Use when a human asks about gas-fired or behind-the-meter power economics for a data center in a US state') and names the exact resource it returns: a per-state brief fusing multiple gas-related data sources. It also explicitly distinguishes itself as the 'GAS analogue of get_grid_intelligence', making its purpose unmistakable against sibling tools.

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 strong when-to-use guidance with concrete example questions, and explicitly states when NOT to use it: for electricity grid headroom use get_grid_intelligence, and for the DCGI score alone use get_gas_index. It also clarifies what is currently returned and what remains withdrawn, so an agent can avoid misuse.

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