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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile needs no restatement. The description earns credit for behavior the annotations cannot convey: the data vintage (last complete fiscal year), the underlying source (FSRS subawards), and the cross-parameter requirement of at least one code or agency — a validation rule not encoded in the schema, where all four parameters are optional. It does not disclose result caps or pagination.

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-loaded with the resource and the fiscal-year scope, then the contents, then the constraints. The telegraphic style ("the teaming and subcontracting leads") and missing punctuation in the constraint sentence make it slightly harder to parse than it needs to be, but there is no filler.

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 a rich four-part return value, the description does the necessary work by listing the three result categories and the joining structure (prime -> subcontractor pairs). Missing pieces are secondary: result volume/limits and what happens when the at-least-one-of rule is violated.

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 per-parameter meanings are already handled; baseline is 3. The description adds one genuinely new semantic — that state filters where the work is performed rather than where the contractor is located — and the at-least-one-of constraint, but says nothing about how naics, psc and agency combine or match.

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 names a specific resource and verb-equivalent ("who does a kind of work") and enumerates exactly what is returned: primes with certifications, FSRS subawards reported by primes, and prime -> subcontractor pairs. It adds a temporal scope ("last complete fiscal year") that no sibling like search_recipients or sbir_awards carries, so the agent can distinguish it without opening 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?

It states a hard precondition — "Give at least one of naics, psc or agency" — and clarifies the role of the optional state filter, which is real usage guidance absent from the schema. It does not name alternatives or say when not to use this tool, so it falls short of the explicit routing seen in top-tier definitions.

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