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

With no annotations, the description carries the full disclosure burden and does so impressively: it reveals that lines are net of grants/fees/state aid, that stage values are separate documents, and that cross-stage comparisons produce misleading growth rates, including a concrete example of the harm. This goes well beyond a generic 'returns history' statement.

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 longer than average, but every sentence carries substantive content—purpose, stage caveat, and net definition—and the core purpose is front-loaded. The real-world example is slightly expansive, but it earns its place by illustrating a non-obvious failure mode; a 5 would require shedding that extra length.

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?

For a two-parameter tool with full schema coverage, the description is nearly complete: it covers the data semantics, the key misuse trap, and the net definition. It doesn't describe the exact return shape, but there is no output schema and the tool is simple enough that this is a modest gap.

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 schema already documents both parameters with 100% coverage, so the baseline is 3. The description adds meaning beyond the schema by explaining why stage is singular and why mixing stages corrupts derived metrics, which is more than the enum alone conveys.

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 opening sentence states precisely what the tool returns—a school budget line's value in each year—and immediately attaches the critical constraint 'AT ONE STAGE.' This makes it easy for an agent to understand the tool's resource and scope and to distinguish it from generic siblings like query or list_datasets.

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?

It explicitly instructs that stage is required and singular, warns against cross-stage comparisons, and explains why comparing actual to budget is a category error. It doesn't name sibling tools or give explicit when-to-use/not-to-use alternatives, so it falls just short of full routing guidance.

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