Skip to main content
Glama
Sign In

Data Sf

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Sf Query

sf_query
Read-onlyIdempotent

Run a raw SoQL query against any San Francisco open-data resource (data.sfgov.org, also written data.sf.gov) by its Socrata id (8-char like "wg3w-h783" or "ebsh-uavg"). Covers SF city purchasing/procurement records (resource id "ebsh-uavg") — real column names fiscal_year, po_dt, purchase_order, purchase_order_line, purchasing_department, purchasing_department_title, commodity_code, commodity_title (the item name/description column — there is no "commodity_description"), vendor_name, vendor_street, vendor_city, vendor_state, vendor_zip_code, vendor_contact, vendor_email, vendor_phone, encumbered_quantity, encumbered_amount — as well as every other SF Socrata dataset by resource id; if you do not already know a dataset's exact column names, omit select (every column comes back) rather than guessing one, since Socrata 400s on an unknown column instead of ignoring it. Full SoQL: where/select/group/order/limit/offset. Use sf_datasets to find a resource id, or sf_recent for the common ones (including "purchasing").

Input Schema

NameRequiredDescriptionDefault
groupNoSoQL $group (e.g. "incident_category").
limitNoMax rows (default 100, max 5000).
orderNoSoQL $order (e.g. "incident_datetime DESC").
whereNoSoQL $where filter (e.g. "incident_year=2025").
offsetNoRow offset for paging.
selectNoSoQL $select (e.g. "incident_category, count(*)").
_apiKeyNoOptional — your own Socrata app token for higher rate limits. Omit to use the keyless endpoint.
resource_idYesSocrata resource id, e.g. "wg3w-h783" (police incidents).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "_apiKey": "your-data-sf-api-key",
+    "limit": 100,
+    "resource_id": "wg3w-h783",
+    "where": "incident_year=2025"
+  },
+  {
+    "_apiKey": "your-data-sf-api-key",
+    "group": "incident_category",
+    "order": "count(*) DESC",
+    "resource_id": "wg3w-h783",
+    "select": "incident_category, count(*)"
+  }
+]
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare this as a safe, read-only, idempotent, open-world query. The description adds useful behavioral detail beyond those hints, notably that Socrata returns a 400 on unknown columns instead of ignoring them and that omitting `select` returns every column.

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

Conciseness4/5

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

The purpose and key guidance are front-loaded, and the long purchasing column list is relevant to avoiding SoQL errors. It is still a dense single paragraph, and some dataset-specific column enumeration could be structured more cleanly.

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?

For a complex query tool with 8 parameters and no output schema, the description covers usage, resource ids, SoQL clauses, and a major error mode well. It does not fully describe the returned row shape or pagination behavior, though the `select` omission note partially covers return fields.

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 schema already documents every parameter, setting the baseline at 3. The description adds real semantic value by naming the supported SoQL clauses, giving resource-id format examples, warning about unknown `select` columns, and listing exact purchasing column names.

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

Purpose5/5

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

The description states a specific verb and resource: 'Run a raw SoQL query against any San Francisco open-data resource' by Socrata resource id. It also names the sibling tools sf_datasets and sf_recent, so an agent can distinguish it from dataset discovery or recent-dataset shortcuts.

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

Usage Guidelines5/5

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

It explicitly says when to use sf_datasets to find a resource id and when sf_recent covers common datasets such as purchasing. It also gives a concrete usage rule: if exact column names are unknown, omit `select` rather than guessing.

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

All Data Sf toolsInspect
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