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. It does this well: it states amounts are in kronor as reported (no recalculation), explains the coverage limitation (~2/3 of companies), and discloses that listed parent companies appear via IFRS consolidated figures marked as such, not as the legal entity. This is rich, honest context. It doesn't mention pagination or response size, but for a financial statement tool this is adequate.

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 a single dense paragraph that front-loads the core purpose and then adds conditional behavior, units, coverage caveat, and IFRS nuance. Every sentence earns its place, though it could be slightly better structured with line breaks or bullet points for the caveats. It's appropriately sized for the complexity.

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 read-only retrieval tool with 2 parameters and no output schema, the description covers the essential context: what data is returned, how the optional parameter changes the result, units, coverage limitations, and a special case (IFRS). The only minor gap is that it doesn't describe the response structure or field names, but since there's no output schema and the tool is a straightforward financial statement fetch, this is a small omission.

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 100%, so the schema already documents both parameters (orgnr and ar). The description adds meaningful context about how 'ar' changes the output (summary vs. post-by-post), which goes beyond the schema's simple 'Räkenskapsårets slutår' description. However, it doesn't add detail about orgnr format beyond what the schema says, so a baseline 3 is appropriate.

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 retrieves a complete income statement and balance sheet from a company's own annual report, distinguishing it from sibling tools like hamta_foretag (company data) and hamta_koncernrelationer (group relations). It also specifies the exact behavior with and without the 'ar' parameter, making the tool's purpose unmistakable.

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 explains when to use the tool (to get bokslut from a company's annual report) and provides a clear conditional: without 'ar' you get all years as a summary, with 'ar' you get the full breakdown post by post. It also notes that only ~2/3 of companies have digital annual reports, so an empty list is expected for others. However, it doesn't explicitly name alternative tools for those cases, so it stops 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.