Search Subawards

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

The description discloses important behavioral quirks beyond the annotations: data coverage starts FY2025, date_from values before the floor are silently clamped rather than rejected, and the response's window block reports what actually ran. It also warns about the missing cage_code field, which prevents a common cross-check operation. These details go well beyond the readOnly/idempotent hints.

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 well-structured: purpose first, then the alternative-tool routing, then a compact bullet list of parameter constraints, then critical data-coverage and schema caveats. Every sentence contributes useful information, and the formatting makes it easy to scan.

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 the most important operational constraints — date-floor clamping, response window disclosure, no cage_code, and key parameter limits — and an output schema exists to cover return-value details. However, with 14 optional parameters and zero schema descriptions, a few parameter formats remain unspecified, such as date string format and accepted sort_by/sort_order values. This is a minor but real 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?

With schema description coverage at 0%, the description adds meaning for several key parameters: prime_uei/sub_uei are exact 12-char, piid is the PRIME contract's PIID, naics must be exactly 6 digits, sub_name is a substring with a 3-char minimum, and limit maxes at 250. However, it leaves other parameters like agency, offset, date_to, amount_min/max, sort_by, and sort_order without any format or value guidance, so the compensation is only partial.

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 verb and resource — 'Search FFATA subawards: who primes paid as subcontractors' — making the tool's function immediately clear. It also distinguishes this search tool from the narrower sibling tools get_prime_subawards and get_prime_relationships, so an agent can tell them apart without inspecting schemas.

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 explicitly states when to prefer alternatives: for a single company's subs-paid or primes-that-paid-them reverse lookups, use get_prime_subawards or get_prime_relationships when you already have one UEI. It also provides a negative usage constraint — there is no cage_code field, so CAGE cross-checking is not possible through this tool.

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