Search government contracts

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

Annotations already declare readOnly/idempotent/non-destructive, so the description correctly spends its words elsewhere: it discloses the pagination contract (has_more, next_cursor, same filters) and the effective default open=true that the schema alone leaves as null. It also discloses two behaviors invisible in structured fields — that agency names are matched to the closest MatchAwards agency and reflected in the result note, and that results should be rendered as markdown links with sam_url for federal notices. Minor gap: no note on result volume or latency expectations.

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 purpose, then a compact filters block, then pagination, then presentation, then exclusions — a sensible order with no filler. The filter enumeration largely duplicates the schema and is the one section that could be trimmed without loss.

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 10-parameter tool with an output schema and rich annotations, everything an agent needs is present: routing in and out, filter interactions that surprise people (state skips federal notices without one, set_aside is federal-only), the paging loop, and output presentation. Return shape is correctly left to the output 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?

Schema coverage is 100%, so the schema already documents every parameter including the deadline-based meaning of open and the NAICS pattern. The description mostly restates the same list; the genuine additions are the example, "Pass several NAICS codes in one call", and stating open's effective default as true where the schema shows default null. That is real but incremental value over a fully documented schema, so the baseline 3 is right.

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?

"Use this when the user wants US federal or state government contract opportunities to bid on: bids, RFPs, solicitations, set-asides" gives a specific verb-plus-resource plus the vocabulary an agent will actually see from users. It names the exact siblings it is not (search_grants, search_jobs, get_opportunity), so routing is unambiguous without opening any 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?

Explicit when-to-use clause up front, explicit exclusions mapped to named alternatives (grants, jobs, single-record details), and an explicit continuation rule for pagination with has_more/cursor. A worked example (naics="238160", state="VA", keyword="roof") anchors the intended call shape.

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