Compare Companies

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

Annotations already indicate read-only, idempotent, non-destructive behavior, lowering the bar. The description goes beyond annotations by warning that amounts are in each company's reporting currency (check `currencies`) and explaining that `antall_ansatte` is a current-value field with null comparison rows. These are critical behavioral caveats that prevent misinterpretation of results.

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 four sentences, each serving a distinct purpose: purpose/scope, use cases, currency warning, and antall_ansatte caveat. It is front-loaded with the primary action and avoids fluff. Every sentence adds value, making it appropriately sized for a tool with these complexities.

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 moderate complexity (comparison, variable years, metric subset, currency differences, headcount quirk), the description covers all key non-obvious aspects. An output schema exists, so the return structure is already documented; the description adds the necessary caveats about currencies and `antall_ansatte` that schema alone would not convey.

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 67% (years lacks description). The description adds meaning to `years` by clarifying it means 'last N years' and emphasizes the side-by-side comparison. It also reinforces `metrics` semantics by listing valid metric names and the special handling of `antall_ansatte`. This partially compensates for the schema gap, though not fully for `years`.

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 compares key financial metrics of up to 5 Norwegian companies side-by-side over a configurable number of years. This specific verb+resource+scope distinguishes it from siblings like get_company_financials (single-company) and search_companies (search). The intended use cases (competitor analysis, benchmark research) further clarify its unique role.

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?

Explicitly says 'Use for competitor analysis, benchmark research or "which of these three companies is the strongest?"' which provides clear when-to-use guidance. However, it does not explicitly mention when not to use it or name alternative tools for single-company financials, so it falls short of a 5.

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