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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds genuinely new context: exact pricing ($0.002 USDC per successful call), the x402 payment rails (Base, Solana, Arc), and the important billing rule that failed calls are not charged. It stops short of disclosing result-set limits, pagination, or behavior when both parameters are passed simultaneously.

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?

Two sentences, no filler, with the register identity and the search-vs-lookup distinction front-loaded before the field enumeration. The long mid-sentence field list ('name, registration date, other names, postal and legal address...') is dense but each item is informative; it is close to being a wall of text.

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?

An output schema exists, yet the description helpfully previews the returned record structure, and pricing/payment mechanics are spelled out — enough for an agent to call it correctly and know the cost. Minor gaps remain around pagination/result caps for the search mode and whether the two optional parameters can be combined.

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 baseline is 3, but the description goes beyond the schema by explaining the semantic distinction between the two parameters: 'name' triggers a search, while 'kennitala' returns the full record. It also restates the 10-digit format and confirms the response fields that kennitala unlocks.

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?

Names the specific register (Fyrirtækjaskrá, Skatturinn) and states both operation modes: search by name/kennitala/address, or fetch the full public record for one company by 10-digit kennitala. The Icelandic jurisdiction and register identity cleanly separate it from the many sibling country registries (brreg Norway, bolagsverket Sweden, ireland_cro, etc.).

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 two supported workflows are clear and the parameter-to-workflow mapping is implied well: pass a name for search, pass a kennitala for the full record. What is missing is explicit routing against siblings (e.g. 'use this only for Icelandic entities; use b2b_brreg_norway_companies for Norway') and any statement about what happens when no parameters are supplied, despite zero required parameters.

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