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

Annotations already signal readOnly and idempotent behavior, and the description adds significant context: market names resolve to their ISO via the DCPI row, balancing authorities return only live generation mix while other figures stay ISO-level, and the reply carries a resolved_from block. The explicit warning that avg_time_to_power_months and avg_queue_wait_months are different measurements with different derivations is particularly valuable and does not contradict any annotation.

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 front-loaded with the trigger question and example, and every block serves a purpose. However, it is very long and repeats some parameter details that already exist in the schema, such as the ISO list and PJM-DOM note; it is thorough but not concise.

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, the description is complete: it covers input modes, resolution behavior, return-field semantics, measurement pitfalls, and exclusions. The output schema exists, so the lengthy field list in the description is a bonus rather than a necessity, and nothing an agent needs to invoke correctly is missing.

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% and the schema descriptions are already good, but the tool description adds meaning beyond them: accepted aliases (iso/region), live EIA balancing-authority examples, market slug examples, the PJM-DOM special zone, and the explicit note that 'market' is not an alias for a grid code. This materially improves correct parameter selection.

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 names a specific deliverable — a grid-headroom and interconnection-queue brief for one ISO — and pairs it with a natural-language trigger question and a concrete example. It explicitly differentiates this tool from compare_isos and get_grid_scoreboard, which is exactly the kind of sibling discrimination an agent needs.

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 tells the agent when to use it (capacity and time-to-power for one ISO) and when not to (comparing 2+ ISOs, global ranking), naming the alternatives. It also explains edge cases like market-name resolution and balancing-authority behavior, leaving little to inference.

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