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

Annotations already cover read-only/idempotent/open-world safety, so the description's value is in the interpretive caveats it adds: Award Amount is a lifetime figure not an FY2025-26 obligation, it is never summed into fiscal-year contract totals, and a File C law link reflects the charged account rather than a judgment. These materially prevent analytic misuse; it stops short of noting the 50-result ceiling's effect on completeness or any auth/rate-limit context.

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?

Front-loads purpose, then filters, then return shape, then caveats — a sensible order with no filler. It is a dense run-on paragraph, however, and the return-field inventory could be tightened.

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, the description carries the return-value burden and does so: recipient, parent, lifetime Award Amount and outlays, verbatim award description, File C law class (labelled/probable/account level only), plus total and truncated counts. Combined with annotations, an agent has everything needed to call and interpret it.

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 every parameter including enums and the 1-50 default-20 limit is already documented. The description restates the filters and default but adds no syntax or edge-case meaning beyond the schema, so the baseline of 3 applies.

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?

States a specific verb and resource ('The largest ICE and CBP awards in the Pay-to-Play Register') plus the ranking key (Award Amount) and the population constraint (component with a transaction in FY2025/26). This clearly separates it from siblings like pay_to_play_totals, pay_to_play_contractor and pay_to_play_committees without needing 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 defines the eligible population and available filters, which implies when the tool applies, but never names an alternative or states when-not to use it (e.g. totals vs contractor-level lookups among the pay_to_play siblings). Usage is inferable rather than spelled out.

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