Search Companies

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

Even with annotations already indicating a safe read-only operation, the description adds substantial behavioral context: case-insensitive substring matching, min 2 chars, the distinction between SAM-only and FPDS-only metrics, and the caveat that a company can show $0 in one metric and millions in the other. It also clarifies that the returned uei is the same identifier accepted by sibling tools.

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 dense but well-structured with a brief opening paragraph and bulleted parameter notes. Every sentence adds distinct semantic value, though it is longer than average; the length is justified by the zero schema coverage and the need to explain field-level return semantics.

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 search tool with six parameters and an output schema, the description covers overall scope, parameter restrictions, sibling alternatives, and return-value semantics thoroughly. The only notable gap is offset/pagination behavior, and the q-required wording creates minor schema friction. Overall, an agent has enough context to select and invoke this tool correctly.

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 0%, so the description carries the full burden. It explains q, naics, agency, naics_small, and limit with useful details like min length and max value. However, offset is not described at all, and q being called REQUIRED conflicts with the schema's nullable/default-null declaration, even if q is semantically necessary for a meaningful search.

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?

Description states a specific verb and resource: 'Search companies that have WON at least one federal award, by name, across both SAM Award Notices and FPDS prime contracts.' It distinguishes itself from search_entities and get_company_profile, so an agent can immediately tell what this tool does and does not do.

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?

Provides explicit routing guidance: use search_entities for ALL registered SAM firms, use get_company_profile for direct UEI lookup, and clarifies that naics/agency/naics_small only narrow an existing name search rather than working standalone. Also notes the Pro-only restriction.

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