Calculate Ordinary Least Squares (OLS) best-fit line (y = mx + c), Pearson correlation coefficient r, and R^2 determination.
| Name | Required | Description | Default |
|---|---|---|---|
| points | Yes | Array of {x, y} coordinate pairs (minimum 2 points) |
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?
No annotations are provided, so the description carries the full burden. It lists the outputs but does not disclose behavior such as whether edge cases (vertical lines, constant y-values, invalid or fewer than 2 points) produce errors, nulls, or approximations. An agent cannot predict failure modes from this description alone.
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, well-formed sentence that front-loads the core purpose and names all three outputs with no filler. Every word contributes to understanding the tool.
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 calculator with one fully documented parameter and clearly named outputs, this description is largely complete. It lacks explicit return structure and edge-case behavior, but the tool's simplicity and the schema coverage make the remaining gap minor.
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 already documents the single 'points' parameter completely, including that each point has x/y and that a minimum of 2 points is required. The description adds no extra parameter-level meaning, which is acceptable given 100% schema coverage, so the baseline score of 3 is appropriate.
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 uses a specific verb ('Calculate') and names three concrete outputs: OLS best-fit line, Pearson r, and R². This clearly distinguishes the tool from the arithmetic/domain calculators in the sibling list and tells an agent exactly what it computes.
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 intended usage is implied by the description and tool name: use it when you need ordinary least squares regression. However, it does not state when not to use it, mention any prerequisites, or reference alternative tools, though no direct regression sibling exists among the provided tools.
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.
Most tools are clearly separated by domain and target calculation, such as rocket_deltav versus projectile_motion or black_scholes versus compound_wealth. A few pairs like home_loan_emi/mortgage_piti and contractor_parity/billable_floor could be initially confused, but the descriptions resolve the intended use cases.
All tool names are lowercase snake_case and generally follow a topic-plus-suffix pattern, which is readable and consistent. The pattern is not a strict verb_noun convention, and acronym-heavy names like feie_nomad_tracker, scorp_optimizer, and casio_991_solve introduce stylistic variance.
At exactly 25 tools, this is at the heavy but still usable end of the scale. The broad spread across tax, finance, engineering, physics, math, and cloud cost makes the server feel more like several domain calculators merged into one service.
Each tool is a self-contained calculation with no missing follow-up operations, so there are no obvious dead ends for the workflows it targets. The main gaps are minor adjacent calculators—such as NPV, depreciation, or broader statistical inference—that agents could work around or obtain elsewhere.
