get_nav_historyGet a mutual-fund scheme's NAV (net asset value) history from MFAPI — fund house, category, ISIN, latest NAV, and the most-recent NAV points (newest first). Use search_schemes to find a scheme_code first (e.g. 118550). Keyless.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of most-recent NAV points to return (default 30, max 120). | |
| scheme_code | Yes | AMFI scheme code, e.g. 118550. Get one from search_schemes. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds value beyond annotations: specifies ordering (newest first), authentication (keyless), and data returned. Annotations already indicate read-only, idempotent, non-destructive, so description complements without contradiction.
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 fluff. First sentence encapsulates purpose and output; second sentence gives usage guidance. Front-loaded with key information.
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?
Given schema and annotations cover safety and parameters, the description is sufficient for a simple data retrieval tool. Could hint at output structure (e.g., returns an array) but not necessary.
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 covers both parameters fully (100% coverage). Description adds ordering context ('most-recent NAV points (newest first)') but does not significantly enhance parameter understanding beyond schema.
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?
Clearly states it gets NAV history of a mutual fund scheme, listing specific fields returned (fund house, category, ISIN, latest NAV, points) and ordering (newest first). Identifies the source (MFAPI) and distinguishes from sibling search_schemes by referencing it as a prerequisite.
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?
Provides explicit prerequisite ('Use search_schemes to find a scheme_code first') and authentication note ('Keyless'). Does not explicitly contrast with siblings like latest_nav, but the context is clear. Could improve by stating when not to use.
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 clear, distinct purpose. The various `ask_pipeworx*` variants are differentiated by mode (single vs grounded vs research). `get_nav_history` vs `latest_nav` serve different query granularities. Administrative tools like `remember`/`recall`/`forget` are clearly separate. No two tools overlap in functionality.
Tool names follow a consistent snake_case convention and generally use `verb_noun` order (e.g., `ask_pipeworx`, `search_schemes`, `validate_claim`). A few exceptions like `entity_profile` (noun_verb) exist, but the pattern is mostly predictable.
At 34 tools, the server is quite large, including many specialized tools (e.g., multiple Polymarket tools, administrative memory/subscription tools) that could arguably be split into separate servers. The number feels slightly excessive for a coherent, focused server.
The tool set covers an extraordinarily wide range of domains: company financials, SEC filings, FDA drugs, economic data, mutual funds, real estate, prediction markets, npm dependencies, AI visibility, and more. It also includes memory, subscription, and feedback mechanisms. There are no obvious gaps for the domains addressed.