dataset_topThe highest (or lowest) rows of the Disclovo dataset by a numeric column — "which is the most/least X".
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| column | Yes | ||
| ascending | No | true for the lowest first; default highest first |
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 must carry behavioral disclosure. It conveys the core behavior (selecting extremal rows by a numeric column) but does not mention limit defaults, tie handling, null behavior, or whether the result is a ranking. The schema supplies ascending and limit constraints, but that is structured data, not behavioral context.
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, front-loaded sentence with no wasted words. The em-dash aside 'which is the most/least X' is slightly redundant with 'highest (or lowest)', but overall it remains concise.
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 description covers the core purpose and clarifies the column type, and the schema covers limit bounds and ascending's default. However, it lacks an explicit statement of what the tool returns (row list vs. ranked table) and edge-case behavior, which is more consequential given no output schema.
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 only 33% (ascending is described). The description adds value by clarifying that column must be numeric, but it does not explain the limit parameter's behavior or defaults, leaving a gap that the schema does not fill.
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 operation: returning the highest or lowest rows of the dataset by a numeric column, with the user intent 'which is the most/least X'. This specifies a verb (rank/select), a resource (rows), and a dimension (numeric column), setting it apart from siblings like dataset_stats (aggregations) and dataset_search (search).
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 phrase 'which is the most/least X' implies a use case, but the description provides no explicit guidance on when to choose this tool over dataset_stats, dataset_search, or dataset_row, and names no exclusions or alternatives.
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 operation: schema introspection, provenance, exact row lookup, substring search, multi-value comparison, statistics, and top/bottom ranking. Despite some overlap among row, compare, and search, the descriptions make the boundaries obvious.
All tools follow the same dataset_ prefix and use short, readable operation names. The naming is uniform and predictable, making it easy for an agent to infer the purpose of each tool.
Seven tools is a well-scoped size for a dataset Q&A server. Each tool provides a distinct capability without unnecessary duplication, and the count is appropriate for the domain.
The tool set covers the core dataset workflow: schema discovery, provenance, row retrieval, search, comparison, statistics, and ranking. Minor gaps exist such as multi-column filtering or distinct-value extraction, but these are not major blockers for typical questions.