dataset_provenanceThe source, the date it was computed, the licence and the citation for the Clientvo dataset. Read this to attribute a figure correctly.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 full burden and it does convey the read-only nature through 'Read this' and the list of metadata fields it returns. It doesn't mention output formatting or error cases, but for a simple provenance lookup this is reasonably transparent.
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 short sentences with no filler. The substantive content is front-loaded in the first sentence, and the usage instruction adds a concrete purpose in the second.
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 no-parameter provenance metadata tool, the description tells the agent what data is returned (source, date, licence, citation) and why to invoke it. There is no output schema, so the description's list of returned elements is sufficient.
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?
There are zero parameters, so the baseline is 4. The description correctly avoids inventing parameter details and instead focuses on what the tool returns.
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 identifies the tool as providing provenance metadata—source, computation date, licence, and citation—for a specific dataset. The phrase 'Read this to attribute a figure correctly' leaves no ambiguity about the tool's purpose, and none of the sibling tools (columns, row, stats, search, etc.) claim this responsibility.
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 explicitly tells the agent when to use it: 'Read this to attribute a figure correctly.' It does not name alternatives or negative conditions, but for a zero-parameter metadata tool alongside data-query siblings, the intended context is clear enough.
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 maps to a clear query type (schema, metadata, exact lookup, substring search, multi-value compare, stats, top-N) with only minor overlap between dataset_row and dataset_compare for single-value filtering. The examples in the descriptions help an agent choose correctly.
All seven tools share the dataset_ prefix and use consistent snake_case with a noun/operation suffix (columns, compare, provenance, row, search, stats, top). This creates a predictable pattern that is easy to extend and select from.
Seven tools is appropriate for a dataset query server: enough to cover common exploration tasks without being overwhelming. Each tool has a distinct role, so the count feels well-scoped rather than padded.
The set covers schema discovery, provenance, exact and fuzzy lookup, comparisons, numeric aggregates, and top/bottom queries — the core operations for a single dataset Q&A server. It lacks a direct 'count rows matching a filter' or distinct-values tool, but agents can work around those with existing tools.