Grid Intelligence

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

Even with annotations declaring read-only and idempotent behavior, the description adds substantial context: it explains the crucial distinction between avg_time_to_power_months and avg_queue_wait_months (with the derivation formula and saturation behavior), notes that balancing authorities return live generation mix while other fields remain ISO-level, and lists the full return structure. This greatly exceeds the annotation coverage.

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 and information-dense but well-structured with a clear order: usage trigger, example, params, returns, and warnings. Every sentence earns its place, though the return-field listing may be redundant given the output schema, and it could be slightly more scannable as a single paragraph.

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 complex tool with many sibling tools and nuanced measurement differences, the description is exceptionally complete. It covers when to use, parameter domains, return fields, metric definitions, and exclusions. The output schema and annotations further support completeness, and the description adds context they lack.

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%, but the description goes beyond by explaining aliases (iso/region), enumerating all 7 ISOs, providing numerous balancing-authority examples, and highlighting the PJM-DOM special case. This adds valuable meaning that the schema alone 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?

The description explicitly states the tool produces a 'grid-headroom + interconnection-queue brief for one ISO' and gives a concrete user-question trigger with an example. It clearly distinguishes from sibling tools like compare_isos and get_grid_scoreboard.

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?

It provides explicit when-to-use guidance ('Use when a user asks...'), an example, and explicit when-not-to-use instructions with alternative tool names. It also clarifies the difference between ISO and balancing-authority scopes and the special PJM-DOM zone.

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