Skip to main content
Glama
Houston Open Data MCP

Houston Open Data MCP

by Sandysmile

Query Houston records

houston_query_records
Read-onlyIdempotent

Query Houston Open Data records with filters, sorting, full-text search, column selection, and pagination; returns up to 100 rows and total match counts.

Instructions

Read rows from a queryable resource, with filters and pagination.

Returns at most 100 rows per call. Use total to count matches without paging through them, for example with a limit of 1. There is no server-side aggregation, so for sums or averages over many rows, page through next_offset. Very long text values are truncated.

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": {
      "resource_id": "<resource_id>"
    },
    "name": "houston_query_records"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoColumn and direction, such as "YEAR desc".
textNoFull-text search across all columns in the table.
columnsNoColumns to return. Omit to return all of them.
filtersNoExact matches by column, such as {"COUNCIL_DISTRICT": "K"}.
paginationNo
resource_idYesResource `id` (UUID) from houston_get_dataset.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered, and the description adds genuinely non-obvious traits: a hard 100-row cap per call, the availability of `total` for counting, absence of server-side aggregation, and truncation of long text values. These are exactly the behaviors an agent needs before planning a query. It stops short of 5 because it says nothing about error behavior, rate limits, or the cost of broad scans.

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?

Four short sentences, front-loaded with the core operation and then the operational limits; each sentence carries distinct information (row cap, counting, aggregation workaround, truncation). Minor waste in discussing response fields that the output schema already documents, but nothing is padded.

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 83% schema coverage, the description only needs to supply the operational envelope, which it does: row cap, counting, aggregation strategy, truncation. For a 6-parameter read tool with rich annotations, this is close to complete. The remaining gap is guidance on how resource_id is obtained and what happens on invalid filters or columns.

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

Parameters3/5

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

Schema description coverage is 83%, so the schema already explains sort, text, columns, filters, pagination, and resource_id in detail. The description adds no parameter-level semantics of its own and instead references `total` and `next_offset`, which are response fields rather than inputs. Baseline 3 is appropriate when the schema carries the parameter burden.

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?

States a concrete verb and resource ("Read rows from a queryable resource") plus the supported capabilities (filters, pagination). It does not name any sibling, but the siblings are all metadata-oriented (search_datasets, get_dataset, describe_table, list_organizations/groups), so the data-retrieval role is distinguishable. Slightly short of 5 because it never explicitly contrasts with those tools.

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?

Gives useful task-level guidance: use `total` to count matches without paging, and page through `next_offset` for sums/averages since there is no server-side aggregation. However, it gives no guidance on when to choose this over houston_search_datasets or houston_describe_table, nor any prerequisite about first resolving resource_id. Usage is implied rather than explicitly routed.

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