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

With no annotations provided, the description must disclose behavior itself, and it does so richly. It reveals that both actual and optimal figures are MLF-adjusted, that the LP objective is solved on MLF-adjusted prices, that only solved LP days are included and failed days are dropped, that calls cannot match get_battery_revenue totals, that date_to may be silently truncated, and that timeouts are possible.

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, but every sentence carries necessary operational or semantic information. It front-loads the core purpose and differentiates the tool from its sibling before covering MLF treatment, dropped days, truncation, and timeout guidance. Nothing in the paper is wasted.

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?

This is a nontrivial tool with no output schema, yet the description anticipates potential misinterpretations and common pitfalls: revenue-total confusion, MLF adjustment, solver-failure days, silent date truncation, and timeout risk. For the complexity of the data returned and the absence of annotations, the description is remarkably complete.

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?

The input schema already provides descriptions and 100% coverage for all three parameters, so a baseline of 3 is appropriate. The description adds meaningful operational semantics beyond the schema: duid restricts to one battery, omitting it scans all DUIDs and risks timeouts, and date ranges should be kept short. This goes beyond the schema's basic type descriptions.

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 opens with a precise statement of what the tool does: 'Actual vs LP-optimal dispatch revenue, per-DUID summary, over a date range'. It explicitly identifies the tool as a benchmark comparison and differentiates it from the sibling tool get_battery_revenue, including the key distinction that this is not a revenue-total source.

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 gives direct guidance on when to use this tool versus an alternative: 'NOT a revenue-total source — use get_battery_revenue for that.' It also provides operational guidance on parameters, explaining that omitting duid scans every DUID and can time out, and advises keeping date ranges short and retrying narrower on timeout.

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