Search Partners

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

Even with readOnlyHint, openWorldHint, idempotentHint, and destructiveHint annotations already present, the description adds meaningful behavioral context: it emphasizes real past performance rather than mere registration, states that results include each firm's `uei`, suggests follow-on chaining to get_company_profile or check_exclusion, and warns about the agency field's limitations with contract-level awarding_agency_code filters. This goes well beyond the annotations.

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 well-structured with an introductory purpose statement, a use-case distinction, a bulleted parameter list, and return/chaining guidance. It is mostly tight and front-loaded, though the appended 'NOTE' is somewhat awkwardly phrased and the emphasis on 'REAL' past performance is slightly redundant with 'not just who's registered for it.' Still, it earns its place overall.

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 tool with 8 optional parameters and no required fields, the description is quite complete: it explains the core use case, differentiates from siblings, documents most parameters, and notes return/chaining behavior. The main missing piece is offset/pagination semantics, and the agency note contains a field-name inconsistency (`agencies` vs. the schema's `agency`). These are minor gaps given the output schema and annotations already provide additional context.

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?

Since schema description coverage is 0%, the description carries the burden of explaining parameters, and it does so well for most fields: naics is exact 6-digit, agency is crosswalk-resolved with examples, state is 2-letter place-of-performance, set_aside lists valid values, psc is exact, keywords match award description, and limit has a max of 50. However, the `offset` parameter is not explained at all, which is a small but real gap in otherwise strong parameter documentation.

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 clearly states the tool's purpose with a specific verb and resource: 'Find teaming/partner firms with REAL past performance, by NAICS + agency + state + set-aside.' It also distinguishes itself from sibling tools by naming search_companies and get_company_peers and explaining the differences. An agent can immediately understand what this tool does and how it differs from nearby alternatives.

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?

The description explicitly frames the tool as answering the 'who could I team with' question and identifies two alternatives: search_companies for open name search and get_company_peers for similarity to one specific company. This gives clear when-to-use guidance and names the siblings it should not be confused with. 'Capture & Teaming tool, Pro only' adds an access constraint as well.

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