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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds real value beyond that: it discloses data provenance (verified ticker matches, source links, exact currency amounts) and a substantive semantic warning that cumulative awards are not accounting backlog and that lifetime obligations differ from transaction flows.

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?

Three sentences, front-loaded with the resource and its enriched fields. The listing of dimensions is dense but purposeful, and the final contrast sentence earns its place as a genuine usage caveat. Slightly overstuffed but not wasteful.

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 15 parameters, no required fields, no output schema and zero schema descriptions, the definition should do more to explain pagination (limit/cursor), date-range semantics, and the query/source/parentId inputs. It covers the domain concept well but leaves enough operational detail unspecified that an agent may construct a suboptimal call.

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 0% across 15 parameters, so the description carries the full burden. It hints at the ticker, jurisdiction, awardType (prime/subawards/modifications), agency, sector, and currency dimensions, but leaves from/to, limit, cursor, query, source, parentId, minAmount, and fiscalYear completely unexplained anywhere, which is a major gap for an agent building a correct call.

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 scope: government prime awards, subawards, modifications, plus the enrichment dimensions (ticker matches, source links, agency concentration, sector rankings). An agent can tell what data it returns. However, it never names or distinguishes itself from the sibling company.award_evidence, so sibling differentiation is left 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?

'Filter by ticker or jurisdiction' gives an implicit pointer to the primary filtering mode, and the closing note signals a semantic caveat about lifetime obligations vs. transaction flows. But there is no explicit when-to-use guidance and no stated alternative such as company.award_evidence, so usage is only implied.

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