dataset_columnsThe columns, which of them are numeric, the row count and the provenance banner of the HomeCover HQ dataset. Call this first to learn the schema.
| 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 provided, the description carries the behavioral disclosure burden. It discloses the exact contents of the response (columns, numeric flags, row count, provenance banner) and implies a safe read operation via 'learn the schema'. It does not discuss error behavior or side effects, but for a zero-parameter inspection tool this is sufficient.
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, no wasted words. The return value list is front-loaded, and the usage guidance is appended in a short, actionable 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 no-parameter tool with no output schema and no annotations, the description fully suffices: it enumerates what the agent will receive and instructs when to call it. Nothing needed for correct invocation is missing.
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 tool has zero parameters and the schema reflects that with 100% coverage, so the baseline is 4. The description correctly omits parameter details and instead focuses on the tool's output, which is all that needs explaining.
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 specific resource (the HomeCover HQ dataset), the action (returning columns, numeric flags, row count, and provenance banner), and distinguishes it from siblings like dataset_stats and dataset_provenance by framing it as the schema-introspection entry point.
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 instruction 'Call this first to learn the schema' provides explicit navigation guidance within the sibling set. It does not name the alternative tools or state when not to use it, but the positional guidance is clear enough for an agent.
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 have clearly distinct purposes: schema, provenance, exact row lookup, substring search, comparison, stats, top values, and enquiry steps are all separate. The only mild ambiguity is between dataset_row, dataset_search, and dataset_compare, but their descriptions clarify exact matching, substring matching, and ordered value comparison respectively.
The dataset_* prefix and enquiry_* prefix create a clear grouping. Within each group the pattern is mostly consistent, though some names are noun-based (dataset_columns, dataset_provenance) while others are verb-based (dataset_search, dataset_compare), and submit_enquiry reverses the prefix order.
Ten tools is a well-scoped set for this domain: seven query tools cover the dataset surface and three cover the enquiry flow. Each tool has a distinct job and none feel redundant.
The dataset side covers schema discovery, provenance, exact lookup, search, comparison, statistics, and ranking, which covers the full range of likely questions. The enquiry side handles explaining the process, listing fields, and submitting with a two-step confirmation, leaving no obvious dead ends.