Get Gas Intelligence

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

The description goes far beyond the annotations by revealing the withdrawal of dcgi_score and gas_to_grid_usd_per_mwh, explaining why (dead interstate-share term, hardcoded constant, 5.5x disagreement) and warning against quoting cached values. It also discloses data handling (null where sparse, never fabricated), per-field provenance (data_basis), and deliberate omissions. This adds critical behavioral context beyond readOnlyHint/idempotentHint.

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?

Though lengthy, the description is tightly packed with essential information, front-loading the use case and then logically covering fusion inputs, return fields, withdrawal notice, and alternatives. Every sentence contributes to effective tool selection and invocation, with clear separation of warnings and guidance. The structure aids scanning, balancing completeness with readability.

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?

Given the tool's complexity (multiple data sources, withdrawal of fields, honest null handling, provenance labels), the description is exhaustive. It explains the return object's key fields, status fields, data_basis, and explicitly states omitted data, ensuring an agent can confidently invoke and interpret results. The presence of an output schema further reduces ambiguity, and the description complements it without redundancy.

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 coverage is 100% with both parameters described. The description adds example formats ('TX' | 'Texas' | 'Virginia') and mentions 'region' as the main param, but this largely mirrors the schema. No additional parameter-specific semantics (e.g., required, optional) are introduced beyond the schema's existing text. Per baseline, high schema coverage yields a 3.

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 explicitly states the tool 'fuses' multiple gas-related data sources into a per-state brief, clearly distinguishing it from siblings like get_grid_intelligence and get_gas_index. It specifies the domain (gas-fired/behind-the-meter power economics for data centers) and the resource (US state), making the purpose unambiguous.

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 opens with 'Use when a human asks about gas-fired or behind-the-meter power economics', provides concrete example questions, and explicitly names alternatives: 'Do NOT use for electricity grid headroom (use get_grid_intelligence) or the DCGI score alone (use get_gas_index).' It also states what is omitted (gas storage, LNG, firm pipeline capacity), giving clear when-to-use and when-not-to-use guidance.

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