get_top_companies

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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so effectively. It describes key behavioral traits: ranking method ('Ranked by job count'), typical output size ('Typically returns 10-20 companies'), data interpretation ('average_salary is ANNUAL in LOCAL CURRENCY'), and limitations ('Smaller great companies may not appear'). The Errors section also discloses potential API issues including rate limits and authentication requirements, which is valuable context not covered by 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 clear sections (PURPOSE, NOTE, Args, Returns, Example, Notes, Errors) that make information easy to locate. While comprehensive, it maintains efficiency with most sentences adding value. The front-loaded purpose statement is excellent, though some sections could be slightly more concise without losing clarity.

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?

Given the tool's complexity (4 parameters, no annotations, but has output schema), the description is remarkably complete. It covers purpose, usage guidelines, parameter semantics, behavioral traits, example output, and error conditions. The output schema exists, so the description appropriately focuses on interpreting the return values rather than just documenting structure. This provides all necessary context for an agent to use the tool effectively.

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 0% schema description coverage, the description fully compensates by providing comprehensive parameter semantics. It explains each parameter's purpose: country filtering with supported codes, keywords for role filtering, location for geographic filtering, and category for job category filtering. It provides specific examples and constraints (e.g., 'ISO 3166-1 alpha-2 country code' with supported values), adding significant meaning beyond what the bare schema provides.

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: 'Get top employers currently hiring, ranked by number of open positions.' It specifies the verb ('get'), resource ('top employers'), and ranking criteria ('by number of open positions'), distinguishing it from sibling tools like search_jobs or get_salary_histogram. The PURPOSE section further elaborates with specific use cases, making the intent unambiguous.

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 provides clear context for when to use this tool: 'Identify major employers in a field' and 'Useful for' scenarios like researching potential employers or understanding market leaders by hiring volume. It explicitly notes limitations ('Shows hiring VOLUME, not company quality') and distinguishes from alternatives by focusing on ranking rather than detailed job searches. However, it doesn't explicitly state when NOT to use it or directly compare to all sibling tools.

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