ai_capacity_index

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

With readOnlyHint=true annotation confirming safe read behavior, the description adds useful behavioral context: it returns top markets with specific fields and refreshes at a scheduled time (Fridays 14:00 UTC). This transparency goes beyond annotations by describing output structure and data freshness, though it could mention that it does not modify state (already implied by readOnlyHint).

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 relatively concise for its informational density, with key purpose front-loaded. Each sentence serves a purpose: stating function, listing return fields, noting refresh schedule, and providing usage/non-usage guidance. Minor redundancy could be trimmed, but overall efficient.

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 has 2 parameters with no enums or output schema, the description covers return fields well (facility_count, operator_count, etc.) and states use cases. However, the parameter meanings are missing, leaving the agent to guess horizon and limit values. Without output schema, the description should also clarify the output type, which it partially does by listing fields.

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 0% and the description fails to clarify the two integer parameters ('horizon' and 'limit'). While 'horizon' is indirectly referenced as 30/60/90 days, the description does not explain that it accepts specific horizon values (e.g., 30, 60, 90) or the meaning of other integers. 'limit' is not mentioned at all. The description adds little parameter-level guidance beyond what the schema provides.

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 clearly states the tool's purpose: ranking data center markets by where 100MW of AI training capacity can land in specific time horizons. It uses a specific verb ('ranks') and resource ('data center markets'), and distinguishes from sibling tools like rank_markets and grid_transition_radar by specifying exactly what question it answers.

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 explicitly states when to use this tool (AI capex planning, GPU cluster siting, hyperscaler deal forecasting) and when not to use it, providing alternative tool names (rank_markets for general best-markets, grid_transition_radar for forward grid-emergence). This gives clear guidance for agent selection.

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