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

With no annotations provided, the description carries the full transparency burden. It discloses what the tool returns (value per country, approximate EUR conversion, source, and validity date) and the error/fallback behavior (returns list of available topics if no match). This goes beyond a minimal statement, though it does not mention potential side effects (none expected) or authentication requirements, which are likely irrelevant for a read-only compare operation.

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 two sentences: the first states the tool's purpose with examples, and the second covers input, output, and error handling. No unnecessary words, front-loaded with the core functionality, and every sentence provides distinct value. It is appropriately concise for the tool's simplicity.

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 no output schema and no annotations, the description fully explains the return format (value per country + EUR conversion + source + date) and the no-match case (list of topics). This is sufficient for an agent to understand what to expect after invocation. The schema covers the two parameters, and the description fills all gaps around behavior and results, making it complete for this tool's complexity.

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?

The schema already describes both parameters (query as metric, topic as optional exact ID), giving 100% coverage. The description adds value by offering concrete examples ('minimum wage', 'vat', 'corporate tax') and clarifying that query accepts natural language while topic is an exact placeholder. It also explains the relationship between the two parameters (either/or) and the fallback behavior when neither matches, enriching the schema's basic meaning.

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 opens with a specific verb and resource: 'compares ONE metric across ALL available countries' (Porovnáva JEDNU metriku naprieč VŠETKÝMI dostupnými krajinami). It lists concrete examples like minimum wage and VAT, and clearly distinguishes itself from sibling tools like search or lookup_fact by focusing on cross-country comparison. The scope ('all countries') and expected output are immediately clear.

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 usage context: either supply a 'query' (free-text metric) or an exact 'topic' ID. It gives examples and explains the fallback behavior when no match is found. However, it does not explicitly name alternatives or state when not to use this tool (e.g., versus lookup_fact for a single country), so it lacks explicit exclusions but still gives enough context to infer appropriate use.

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