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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable behavioral context beyond that: the critical warning that avg_time_to_power_months and avg_queue_wait_months are different measurements with different derivations, the market-to-ISO resolution behavior with the resolved_from block, and the balancing-authority versus ISO data-granularity caveat. There is no contradiction with the annotations.

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 phrase and a concrete example, then moves through params, returns, and caveats. It is dense and long, but nearly every sentence carries operative information, including the metric-distinction warning and sibling exclusions. The only slight drawback is that it reads as a wall of text; a little structuring could make it more scannable, but it is not padded.

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 (6 params, multiple input modes, a rich output schema, and subtle metric distinctions), the description is exceptionally complete. It covers parameter aliases, market vs ISO resolution, balancing-authority scope limits, the resolved_from behavior, the full return list, the non-interchangeability of two time metrics, and sibling tool routing. Nothing an agent needs to call it 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 description coverage is 100%, so baseline is 3, but the description goes well beyond the schema. It explains alias behavior (iso/region accepted for region_id), the semantic difference between market= and region_id=, the market-resolution process, the PJM-DOM zone case, and even the mpp_pay/mpp_credential payment flow. This is rich semantic clarification that the schema alone does not provide.

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 leads with the exact user question it answers ('can I get N MW of power in <ISO> and how long will it take?') and names the tool as the 'flagship grid-headroom + interconnection-queue brief for one ISO'. It gives a concrete PJM example and explicitly distinguishes itself from compare_isos and get_grid_scoreboard, so an agent can tell it apart from siblings without opening their schemas.

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?

Opens with 'Use when a user asks...' and includes a realistic example showing region_id='PJM'. It explicitly states when NOT to use the tool ('Do NOT use to compare 2+ ISOs side-by-side (use compare_isos) or for the global greenest-first ranking (use get_grid_scoreboard)'), naming the exact alternatives. This is fully explicit guidance.

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