Get NPS reference datasets: aum, fees, contributions, exits, disclosures, snapshots, top holdings, or benchmark returns.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Reference dataset to return | aum |
| limit | No | Max rows (default: 200, max: 500) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only uses the verb 'Get' implying a read operation, but provides no context on pagination, response format, errors, or rate limits. The schema's limit parameter is not mentioned.
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 concise sentence that front-loads the purpose and enumerates the main types. It is efficient, but the incomplete enumeration prevents a perfect score, as it could confuse agents relying on the prose.
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 annotations and no output schema, so the description is the only source of context. It does not explain when to choose this over siblings, omits valid types, and discloses no behavior. Given the large sibling set, more context is needed for correct selection and invocation.
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% and describes both parameters, giving a baseline of 3. However, the description's list of dataset types is incomplete (missing portfolio_holdings and portfolio_metrics), which can mislead agents into thinking only 8 types exist. It adds no extra meaning for the limit parameter.
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 NPS reference datasets and enumerates several dataset types, distinguishing it from siblings like get_nps_holdings and get_nps_metrics. However, it omits two enum values (portfolio_holdings, portfolio_metrics) visible in the schema, which slightly weakens completeness.
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?
There is no guidance on when to use this tool versus the many NPS-related siblings (e.g., get_nps_holdings, get_nps_metrics, get_nps_nav_history). The description only states what it returns, without any when-to-use or alternative exclusions.
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.
Tools are mostly distinct, with clear prefixes (gift, nps, sif) separating fund types. Some overlap exists among metrics/returns tools, but descriptions clarify their specific scope. Overall, an agent can differentiate tools without much ambiguity.
All tools follow a consistent snake_case verb_noun pattern (e.g., get_fund, list_categories, screen_funds). Verbs are standardized (get, list, search, compare, find, screen), making the API predictable and easy to navigate.
At 28 tools, the set exceeds the 'too many' threshold. While the domain covers multiple fund types, the count is excessive; several tools (e.g., get_metrics, get_gift_metrics, get_nps_metrics) could be consolidated with parameters. This may overwhelm agents.
The tool surface is comprehensive for a read-only mutual fund data server. It covers search, comparison, screening, NAV history, holdings, quantitative metrics, benchmarks, and specialized segments (GIFT, NPS, SIF). No critical gaps were identified.
