Fulltextovo nájde fakty v corpuse (SK dane/mzdy/odvody/termíny). Vráti zoradené zhody s hodnotou a zdrojom.
| Name | Required | Description | Default |
|---|---|---|---|
| agent | No | Voliteľné: meno volajúceho agenta (pre štatistiku hľadaní) | |
| limit | No | Max počet výsledkov (default 8) | |
| query | Yes | Dopyt, napr. "minimálna mzda 2026" | |
| country | No | Voliteľný filter krajiny (napr. SK) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that results are sorted and include value and source, which is useful. However, it does not mention whether the tool is read-only, any permissions, rate limits, or side effects. For a search tool, the return description is helpful but leaving out operational context limits transparency.
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 sentence that is appropriately sized and front-loaded with the core action and scope. It efficiently mentions the return format with no redundant information, earning its place.
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?
The tool has no output schema and no annotations, so the description must cover return values and usage context. It explains that results are sorted matches with value and source, which is the key output. However, it lacks details on the 'country' parameter's impact, the nature of 'facts', or any limitations, leaving room for ambiguity in more complex scenarios.
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 covers 100% of parameters with detailed descriptions, so the baseline is 3. The tool description adds no additional parameter semantics beyond the schema, but the schema itself already explains query, limit, country, and agent adequately.
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 performs fulltext search over a corpus of facts (SK taxes/wages/levies/deadlines), with the verb 'nájde' (finds) and a specific resource. It distinguishes itself from siblings like lookup_fact or list_facts by emphasizing 'fulltext' search, though it does not explicitly contrast with them.
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 no guidance on when to use this tool versus alternatives. It does not mention any exclusions or conditions, only stating what the tool does. The usage context is implied by 'fulltext' but no explicit direction is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: compare for cross-country metric comparison, list_facts for enumeration, lookup_fact for ID-based retrieval, search for fulltext search, and the three post tools target forum vs. blog with update restrictions. No two tools could be easily confused.
Most tools follow a verb_noun pattern (list_facts, lookup_fact, post_message, publish_post, update_post), but compare and search are single verbs, creating a minor stylistic inconsistency that is still readable and predictable.
Seven tools is well-scoped for a facts corpus server: four retrieval methods and three community interaction methods, each earning its place without bloat or sparsity.
The tool surface fully covers the expected domain: fact retrieval (search, list, lookup, compare) and community contribution (post forum messages, publish blog posts, update own posts). No obvious gaps or dead ends; deletion is intentionally absent and compensated by update.