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

Annotations already declare readOnly, idempotent, open-world and non-destructive, so the safety bar is covered. The description adds genuinely useful context beyond them: the upstream source (USAspending.gov) and a concrete price of $0.004 per award, which an agent needs for cost-aware invocation. It stops short of disclosing pagination/row-limit behavior or result-ordering caveats beyond what the sortBy schema field already says.

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 action and dataset, then a single dense clause covering returned attributes and use cases, with pricing isolated on its own line. Every clause carries information and nothing is repeated from the schema or title.

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 14-parameter tool with no output schema, the description does the heavy lifting by enumerating exactly what comes back per award, so the agent knows the response shape. Remaining gaps are minor: it does not flag that awardTypes defaults to contracts only (so grants/loans are excluded unless requested) nor discuss result caps, both of which live only in the schema.

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 100% schema description coverage across all 14 parameters, the schema already carries the semantics and the baseline of 3 applies. The description mentions the same facets the parameters expose (NAICS, PSC, assistance listing, place of performance, tickers/parent company) but adds no extra syntax, matching rules or interaction details beyond the schema text.

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?

Opens with a specific verb and resource ("Get US federal contracts, grants and loans") and enumerates the returned attributes — winner, agency, amount, date, NAICS/PSC/assistance listing, place of performance, parent company and ticker. "from every agency (USAspending.gov)" implicitly separates it from the DoD-only sibling dod_contract_awards, but the sibling is never named outright, so differentiation is left partly to inference.

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?

Gives intended audiences ("sales intelligence, investors measuring government revenue exposure, and procurement or policy research"), which implies when the tool is a fit. It never states when NOT to use it, nor routes the agent to alternatives such as dod_contract_awards for DoD-specific work or eu_tenders for non-US procurement, so the selection logic stays implicit.

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