Skip to main content
Glama
Sign In
skylight-mcp

skylight-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

skylight_list_rewards

Read-only

Lists rewards for a Skylight frame, with optional redemption date range and unredeemed items marked by null redeemed_at.

Instructions

List rewards for a Skylight frame. The redeemed_at_min/redeemed_at_max window defaults to the last 30 days, but the endpoint returns every reward, with redeemed_at null for one not yet redeemed. Each reward carries its owner in category_id (a family-member category — resolve names via skylight_list_categories), pluralised to category_ids when the API links several members.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "skylight_list_rewards"
  }
}

Input Schema

NameRequiredDescriptionDefault
frameIdNo
redeemed_at_maxNo
redeemed_at_minNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.1
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. First observedv0.4.6

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, yet the description adds real behavioral context: the redeemed_at_min/max window defaults to 30 days but the endpoint actually returns every reward, with redeemed_at null for unredeemed ones. That default-vs-actual distinction is exactly the kind of trap that would mislead an agent, and it is disclosed. Pagination and result-size behavior remain unmentioned.

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?

Three tight sentences that front-load purpose before the behavioral caveat and the owner-resolution detail. Every sentence carries information, though the trailing pluralisation note ('category_ids' when several members are linked) is dense and slightly cryptic without an example.

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 no output schema, the description correctly takes on the burden of describing the response shape — rewards with a nullable redeemed_at and an owner encoded in category_id/category_ids. For a read-only, three-parameter listing tool this covers what an agent needs to interpret results, missing only the broader field set of a reward object.

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 the parameters, and it does explain the redeemed_at_min/max window semantics and ties frameId to 'a Skylight frame'. It still omits the date format expected for the bounds and does not note that all three parameters are optional, so compensation is partial.

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?

Opens with a specific verb and resource ('List rewards for a Skylight frame'), which is unambiguous and clearly distinct from the list_chores/list_tasks/list_lists siblings. It does not explicitly contrast itself with any alternative, but the resource is unique enough that an agent can select it without hesitation.

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 description clarifies the default 30-day window and points at skylight_list_categories for resolving owner names, which is a genuine routing hint. However, it never says when to reach for this tool versus another, nor does it state whether frameId is required or what happens when it is omitted.

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

Deploy Server

Other Tools