Skip to main content
Glama

Free Official Data Samples, Provenance, Aggregations & Insights

Request a feature, payment method, data or endpoint

request_capability

Free, no signup. Request any feature, including payment methods we do not yet support. Examples include finding live parking by facility, comparing school district finances across states with local-cost-adjusted spending per student, downloading CSV results, or requesting PayPal or Bitcoin Lightning. For payment requests, name the method and the agent task it would enable. Dataset capabilities require dataset; endpoint/suggestion require description (10-800 characters), no dataset needed. Use public examples, never credentials or personal information. Retain the private receipt/status_url. A receipt confirms recording, not support, delivery or a review date.

Input Schema

NameRequiredDescriptionDefault
datasetNo
capabilityYes
source_urlNo
descriptionNo
example_queryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / allOf
      Added value: +[
      +  {
      +    "else": {
      +      "required": [
      +        "dataset"
      +      ]
      +    },
      +    "if": {
      +      "properties": {
      +        "capability": {
      +          "enum": [
      +            "endpoint",
      +            "suggestion"
      +          ]
      +        }
      +      }
      +    },
      +    "then": {
      +      "properties": {
      +        "description": {
      +          "minLength": 10
      +        }
      +      },
      +      "required": [
      +        "description"
      +      ]
      +    }
      +  }
      +]
    • changedInput schema / properties / capability / enum
      Previous value: -[
      -  "dataset",
      -  "filter",
      -  "aggregation",
      -  "insight",
      -  "freshness",
      -  "export"
      -]New value: +[
      +  "dataset",
      +  "filter",
      +  "aggregation",
      +  "insight",
      +  "freshness",
      +  "export",
      +  "endpoint",
      +  "suggestion"
      +]
    • addedInput schema / properties / description
      Added value: +{
      +  "maxLength": 800,
      +  "type": "string"
      +}
    • addedInput schema / properties / source_url / maxLength
      Added value: +500
    • changedInput schema / required
      Previous value: -[
      -  "dataset",
      -  "capability"
      -]New value: +[
      +  "capability"
      +]
  2. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description discloses outcome semantics that an agent could not otherwise know: a receipt confirms recording only, not support, delivery or a review date, and the private receipt/status_url must be retained for later status checks. It also states a privacy constraint (public examples only, never credentials or personal information), which is meaningful for a submission tool. No contradiction with the annotations.

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?

Front-loaded with the value proposition ("Free, no signup") followed by examples, requirements, then caveats, so an agent can stop reading once it has what it needs. The example list is longer than strictly necessary, but each example illustrates a distinct request class rather than padding.

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 5-parameter, 0%-coverage submission tool with no output schema, the description covers the conditional requirements, the privacy boundary, and what the returned receipt does and does not mean. The remaining gap is that it does not mention how to follow up on a request (the get_capability_request_status sibling) or what source_url and example_query are for.

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 0%, so the description must carry parameter meaning. It does explain the conditional dataset-vs-description requirement that mirrors the schema's allOf, but it says nothing about source_url or example_query, and the enum values filter/aggregation/insight/freshness/export are never distinguished from dataset/endpoint/suggestion. Minimum viable rather than complete.

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 uses a specific verb ("Request") and enumerates the requestable resources: features, payment methods, datasets, endpoints and suggestions, with concrete examples. This lets an agent tell it apart from get_capability_request_status or request_paid_access, though it never names those siblings explicitly.

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

Usage Guidelines4/5

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

It gives clear conditional rules: dataset-type capabilities require a dataset, endpoint/suggestion require a 10-800 char description and no dataset, and payment requests must name the method plus the agent task it enables. It stops short of explicit exclusions or pointing to alternatives like request_paid_access for paid access.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources