Brent Burgess

Read one of the site’s data tables

query_dataset

Read-onlyIdempotent

The rows of one table behind this site’s data page, oldest first, with each column’s type and meaning. Filter by date with from and to (YYYY-MM-DD), which apply to the table’s date column; if more rows match than the limit, the most recent are returned. Daily and weekly tables keep about a year.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "dataset": "<dataset>"
    },
    "name": "query_dataset"
  }
}

Input Schema

Name	Required	Description
`to`	No	The latest date to include
`from`	No	The earliest date to include
`limit`	No	How many rows to return at most, 1 to 500
`dataset`	Yes	Which table, as get_site_stats lists them

Output Schema

Name	Required	Description
`url`	Yes	Where /data shows it
`rows`	Yes	The rows, oldest first
`grain`	Yes	One row per
`notes`	Yes	What /data says about these numbers, word for word
`title`	Yes	What it holds
`total`	Yes	How many rows matched
`columns`	Yes	The columns, in order
`dataset`	Yes	The table
`returned`	Yes	How many rows were returned
`rows_from`	Yes	The first date kept; older rows are left out of the server. Null when every row is kept.
`truncated`	Yes	Whether more rows matched than were returned
`date_column`	Yes	The column from and to apply to, or null if the table has none
`description`	Yes	What a row is
`data_through`	Yes	The last day the data covers

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 8, 2026

changedInput schema / properties / dataset / enum

Previous value: -[
-  "agg_ci_steps_30d",
-  "agg_countries_monthly",
-  "agg_pages_monthly",
-  "fct_checks",
-  "fct_ci_daily",
-  "fct_crawlers_weekly",
-  "fct_font_daily",
-  "fct_github_monthly",
-  "fct_github_weekly",
-  "fct_pipeline_runs",
-  "fct_probes_weekly",
-  "fct_reading_daily"
-]New value: +[
+  "agg_ci_steps_30d",
+  "agg_countries_monthly",
+  "agg_pages_monthly",
+  "fct_checks",
+  "fct_ci_daily",
+  "fct_crawlers_weekly",
+  "fct_font_daily",
+  "fct_github_monthly",
+  "fct_github_weekly",
+  "fct_merge_to_live",
+  "fct_pipeline_runs",
+  "fct_probes_weekly",
+  "fct_reading_daily"
+]

changedOutput schema / properties / dataset / enum

Previous value: -[
-  "agg_ci_steps_30d",
-  "agg_countries_monthly",
-  "agg_pages_monthly",
-  "fct_checks",
-  "fct_ci_daily",
-  "fct_crawlers_weekly",
-  "fct_font_daily",
-  "fct_github_monthly",
-  "fct_github_weekly",
-  "fct_pipeline_runs",
-  "fct_probes_weekly",
-  "fct_reading_daily"
-]New value: +[
+  "agg_ci_steps_30d",
+  "agg_countries_monthly",
+  "agg_pages_monthly",
+  "fct_checks",
+  "fct_ci_daily",
+  "fct_crawlers_weekly",
+  "fct_font_daily",
+  "fct_github_monthly",
+  "fct_github_weekly",
+  "fct_merge_to_live",
+  "fct_pipeline_runs",
+  "fct_probes_weekly",
+  "fct_reading_daily"
+]

First observedOct 20, 2026

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, non-destructive and closed-world behavior, so the bar is lower. The description still adds real non-obvious traits: rows come oldest first, but when matches exceed the limit the most recent rows are returned (a truncation rule that conflicts with naive ordering intuition), and daily/weekly tables retain only about a year.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, no filler, and the most decision-relevant facts (what you get, how to filter, what happens at the limit, retention horizon) are front-loaded. Nothing is repeated from the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and full annotation coverage, the description need not explain return values, and it does supply the ordering, truncation and retention context an agent needs. The only minor gap is that it never sets expectations for invalid or empty dataset/date combinations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description goes beyond the schema by explaining that from/to are YYYY-MM-DD and bind to the table's own date column, and by clarifying the truncation semantics of limit rather than just its range.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('The rows of one table behind this site's data page') and adds the shape of the payload (column types and meanings, oldest first). It distinguishes itself from get_site_stats by tying the dataset enum back to that tool, though it doesn't explicitly say how it differs from siblings like list_content or search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: the agent can infer this is the tool for raw row-level table data, and it learns the date filters apply to the table's date column. There is no explicit when-to-use vs. when-not guidance, no named alternative for aggregate summaries, and no prerequisites mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Brent Burgess tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?