Search across Bulgarian pension legal framework documents.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search term (e.g., "чл. 175", "equity limits", "инвестиционни ограничения"). | |
| document | No | Optional filter to search only one document. | |
| max_results | No | Maximum number of matching sections to return (default 10). |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
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, but it discloses nothing beyond the basic search intent. There is no mention of read-only nature, result snippet behavior, pagination, or any side effects, leaving the agent with significant uncertainty.
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, front-loaded sentence with no redundant wording. Every word contributes to stating the tool's purpose, making it highly concise and efficient.
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 existence of an output schema reduces the need to explain return values, but the description still lacks critical context such as search behavior (e.g., whether it matches exact phrases or stems), result ordering, or document coverage. It is minimally viable but leaves gaps for an AI agent choosing how to phrase queries.
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 input schema already provides 100% coverage with descriptions for all three parameters, including examples for the query. The description adds no additional semantic value about parameters, so the baseline score of 3 applies.
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 specifies the action ('Search') and the resource ('Bulgarian pension legal framework documents'), which is a distinct verb from sibling tools like 'get_pension_legal_framework'. It does not elaborate on search scope (e.g., full-text vs. metadata), but it is unambiguous about the tool's core function.
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 choose this tool over alternatives. It does not mention when to use a search versus retrieving the full framework (e.g., get_pension_legal_framework), nor does it state any exclusions or prerequisites.
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.
Many tools have identical aliases (e.g., list_funds and get_bulgarian_pension_funds, list_benchmarks and get_bulgarian_pension_benchmarks), creating ambiguity. An agent would struggle to choose between them. Additionally, cache_stats is unrelated to the core domain, adding confusion.
Naming patterns are inconsistent: some tools use short verb_noun (list_funds, compute_metric), while aliases are long and verbose (get_bulgarian_pension_fund_managers). Mixing both styles without clear distinction harms predictability.
26 tools is on the high side, but many are aliases; the unique tool count is around 16-17, which is reasonable for a comprehensive analytics server. However, the alias redundancy makes the list feel bloated.
The tool set covers discovery (list_funds, list_managers, list_benchmarks), data retrieval (get_nav_series, get_holdings_reports_index), computation (compute_metric, rank), simulation (simulate_saver_outcome), and legal documents (search_pension_law). Missing are tools for updating or creating data, which is acceptable for an analytics server. A minor gap is the lack of a direct fund detail tool besides NAV.
