Save a Sift query to the account. Saving under a name that already exists replaces that scan rather than creating a second one.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | what to call the scan; saving over an existing name revises it | |
| source | Yes | the Sift query | |
| universe | No | liquidity universe: 100, 500 (default) or 2000 |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosing side effects, and it does disclose the key mutating behavior: saving under an existing name replaces the scan rather than creating a duplicate. It does not discuss permissions or irreversibility, but the core impact on account state is clear.
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 with no filler. The primary action is front-loaded, and the critical overwrite behavior is stated compactly in the second sentence.
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 simple tool with only three parameters and no output schema, the description covers the essential purpose and the non-obvious replace behavior. It does not describe return values, but no output schema exists and the invocation semantics are clear.
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 description coverage is 100%, so the baseline of 3 applies. The description adds no parameter-level detail beyond the schema, and the overwrite behavior is already reflected in the schema's description of the name 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 states a specific verb and resource: saving a Sift query to the account. It also clarifies the upsert behavior, which distinguishes it from siblings like run_scan, delete_scan, and list_saved_scans. No ambiguity remains about what the tool does.
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 implies the tool is used to persist queries and explains what happens when saving under an existing name. However, it does not explicitly state when to use this over siblings such as run_scan or list_saved_scans, nor does it mention 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.
Each tool targets a clearly distinct action: symbol discovery, symbol metadata, price bars, query reference, scan execution, saved scan management, market metadata, and historical replay. run_scan and hitrate are differentiated as current matches versus past performance, so there is no meaningful overlap.
Most tool names follow a lowercase snake_case verb_noun pattern such as delete_scan, get_bars, run_scan, save_scan, and search_symbols. A few names like hitrate, market_meta, and sift_reference break that pattern but remain consistent in style and readable.
Ten tools is well-scoped for an NSE stock screener. Each tool earns its place and together they cover symbol lookup, market data, querying, saved scan lifecycle, and historical evaluation without redundancy.
The core screener workflow is covered: find symbols, fetch bars and metadata, learn the query language, run scans, manage saved scans, and evaluate hit rates. Minor gaps exist, such as no dedicated view for a single saved scan's full query and get_bars only returning recent bars, but these are workable limitations.
