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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds valuable behavioral context beyond annotations: that document kinds remain separate and no value is preferred or reconciled, and that the source is under redistribution review. It does not cover pagination or response shape, but the output schema exists.

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 purpose and data-semantics sentences are front-loaded and earn their place, but the third sentence is bloated with pricing, refund policy, and a URL that an agent invoking the tool does not need. The fourth sentence about the free-query exclusion is useful, but the pricing detail could be trimmed without losing selection or invocation value.

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?

The description covers purpose, key data semantics, and access requirements well, and the output schema relieves it of explaining return values. However, it leaves the only parameter unexplained in practical terms—no guidance on how to pass document kind, auction, delivery year, or resource class into the opaque params object—so an agent could still invoke it incorrectly.

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 0% and the single 'params' object is opaque with additionalProperties true. The description partially compensates by naming the intended filter dimensions (document kind, auction, delivery year, resource class), but it does not explain how to structure those filters inside the params object or what values are valid, leaving meaningful ambiguity.

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 first sentence names a specific verb (query) and resource (cited PJM marginal ELCC class ratings) and lists the filter axes, immediately distinguishing it from the MISO sibling and the broader capacity-market tools. An agent can tell what dataset this returns without opening the schema.

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 implies usage context (requires a paid API key, not in the 25 free queries) and notes that preliminary/final/incremental documents are not reconciled, which helps an agent understand what to do with the results. However, it never states when to choose this tool over query_power_capacity_accreditation_miso_v1, query_power_capacity_market_pjm_v1, or the describe_* variants, nor does it name any alternative.

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