dataset_statscount, min, max, mean, median and sum of a numeric column of the Runwayze dataset (grouping commas and currency are handled; non-numeric rows are excluded and counted).
| Name | Required | Description | Default |
|---|---|---|---|
| column | Yes |
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 provided, the description must carry the full behavioral burden. It discloses that grouping commas and currency are handled, and that non-numeric rows are excluded and counted. However, it does not mention error behavior (e.g., column not found), edge cases (all rows non-numeric), or the exact return format. This is adequate for a simple tool but leaves some gaps.
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-structured sentence. It front-loads the list of statistics, then adds the crucial handling details. There is no waste; every clause adds value.
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 one-parameter tool with no output schema, the description covers the core functionality, the column type expectation, and the handling of non-numeric and formatted values. It does not discuss error cases or return shape, but these are minor given the simplicity and the distinct sibling set. Overall, it is nearly complete.
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 provides only a 'column' string with minLength 1 and no description, so schema coverage is 0%. The description compensates by clarifying that the column must be numeric and that formatted numbers (commas, currency) are accepted, adding meaning beyond the raw schema. It does not provide examples but is sufficient for a single 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 (compute) and resource (numeric column of the Runwayze dataset), and enumerates the exact statistics produced (count, min, max, mean, median, sum). This distinguishes it from all siblings, which handle columns, comparisons, provenance, rows, search, and top values—none of which compute summary statistics.
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 usage for numeric columns and notes how non-numeric rows are handled, but it does not explicitly state when to use this tool versus alternatives or when not to use it. Given the siblings are clearly different in purpose, the implication is strong, but no direct guidance or exclusions are provided.
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 distinct role: schema, provenance, exact match, substring search, multi-value comparison, numeric stats, and top-N. There is some overlap between the row retrieval tools, but the descriptions clarify the matching semantics enough to avoid serious confusion.
All tools share a consistent dataset_ prefix and are concise, but they mix noun-style names (dataset_columns, dataset_provenance, dataset_row, dataset_stats) with verb/adjective-style names (dataset_compare, dataset_search, dataset_top). The pattern is still predictable and readable.
Seven tools is well-scoped for a read-only dataset query server. Each tool covers a distinct query mode or metadata need, so none feel redundant or excessive.
The tool set covers schema discovery, provenance, exact lookup, fuzzy search, multi-value comparison, numeric aggregations, and top/bottom ranking. A minor gap is the lack of a generic sample/all-rows or distinct-value exploration tool, but the core question-answering workflows are well supported.