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

Annotations only declare read-only, idempotent, open-world access; the description goes well beyond that by disclosing that blocks must never be summed, that DOD contract records arrive at USAspending roughly 90 days late, that FY2026 is partial as of an as-of date, and that answers must carry source, licence and the FEC 52 U.S.C. 30111(a)(4) restriction. It also sets a disclosure policy: institutions only, withheld recipients shown as counts, no party labels.

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 runs several hundred words in a handful of enormous multi-clause sentences, mixing what the tool returns with editorial policy, legal boilerplate and exclusions. Front-loading is decent, but the density makes the operative rules (never sum blocks, side columns are separate) hard to extract at a glance.

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?

With no output schema and no parameters, the description must carry the full result shape, and it does: it enumerates the blocks, the fiscal-year breakdown, the termination windows, the DHS campaign task orders, the specific Treasury accounts, side columns and exclusions. What it omits is the actual response structure or key names, which an agent would still have to discover at call time.

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 tool takes no parameters, so the schema carries nothing to explain and the baseline of 4 applies. The description does not add spurious parameter talk, though it also gives no hint of any optional scoping such as fiscal year or block 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 opening clause states a specific verb and resource: totals from the Media Money Register, covering federal media money FY2017-FY2026 across named recipient families. That is far more informative than the title. It never names media_money_family, media_money_terminations or media_money_advertising, however, even though its own contents explicitly include per-family splits, termination actions and advertising figures, so an agent cannot tell from the text which of those siblings to pick instead.

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?

There is no statement of when to call this versus the three sibling tools that overlap its content, nor any prerequisite or exclusion about tool choice. The many 'never added' rules govern how to read the numbers, not when to invoke the tool, so the agent is left to infer routing from the name alone.

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