io.github.cyanheads/usaspending-mcp-server: tool descriptions scored

tools/list taken: 2026-11-02 (UTC)
From: Official MCP Registry
Connected to: https://usaspending.caseyjhand.com/mcp
Repository: github.com/cyanheads/usaspending-mcp-server
Scoring rules: v2
Removal: support@forecall.dev

Scores, issues and names only

This page shows how io.github.cyanheads/usaspending-mcp-server's tool descriptions scored, the issues found and the names of its tools and parameters. The descriptions are the server's own: read them where the copy came from.

Forecall asked the URL this server lists in the official MCP Registry for its tools/list once, on the date above, without calling any tool. The server may have changed since.

servers/io.github.cyanheads/usaspending-mcp-server

Average score: 70.7 / 100Clear
Tools: 18
Near-identical descriptions: 0

Across the server

No server-wide issues.

Tools

usaspending_spending_by_geography

62 / 100Cloudy

Purpose: 17 / 20
When to use: 0 / 20
Arguments: 22 / 25
Return value: 8 / 15
Constraints and side effects: 10 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context

usaspending_disaster_spending

64 / 100Cloudy

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 24 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context

usaspending_get_award_subawards

65 / 100Cloudy

Purpose: 20 / 20
When to use: 5 / 20
Arguments: 25 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

Minor
The description mentions none of its 3 or more arguments.params_not_in_description
Minor
Required identifiers whose description does not say where the value comes from: award_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

usaspending_get_award_transactions

65 / 100Cloudy

Purpose: 20 / 20
When to use: 5 / 20
Arguments: 25 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

Minor
The description mentions none of its 3 or more arguments.params_not_in_description

usaspending_get_recipient

65 / 100Cloudy

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 25 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context

usaspending_spending_by_category

66 / 100Cloudy

Purpose: 17 / 20
When to use: 0 / 20
Arguments: 22 / 25
Return value: 15 / 15
Constraints and side effects: 7 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context

usaspending_list_agencies

67 / 100Cloudy

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 22 / 25
Return value: 15 / 15
Constraints and side effects: 10 / 10
Examples: 0 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Minor
No `required` list, so every argument is optional.no_required

usaspending_autocomplete_filters

69 / 100Cloudy

Purpose: 17 / 20
When to use: 5 / 20
Arguments: 25 / 25
Return value: 15 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

No issues.

usaspending_spending_over_time

69 / 100Cloudy

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 22 / 25
Return value: 15 / 15
Constraints and side effects: 7 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Minor
The description mentions none of its 3 or more arguments.params_not_in_description

usaspending_get_idv_awards

70 / 100Clear

Purpose: 20 / 20
When to use: 5 / 20
Arguments: 25 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 5 / 10

No issues.

usaspending_search_recipients

70 / 100Clear

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 25 / 25
Return value: 15 / 15
Constraints and side effects: 10 / 10
Examples: 0 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context

usaspending_search_federal_accounts

71 / 100Clear

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 19 / 25
Return value: 15 / 15
Constraints and side effects: 7 / 10
Examples: 10 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Minor
No `required` list, so every argument is optional.no_required

usaspending_search_awards

73 / 100Clear

Purpose: 20 / 20
When to use: 5 / 20
Arguments: 18 / 25
Return value: 15 / 15
Constraints and side effects: 10 / 10
Examples: 5 / 10

Minor
String arguments with no constraint or example: location_filter.city.loose_string_param
Minor
No `required` list, so every argument is optional.no_required

usaspending_get_federal_account_breakdown

75 / 100Clear

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 25 / 25
Return value: 15 / 15
Constraints and side effects: 10 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Minor
The name is long (41 characters).long_name

usaspending_get_agency

77 / 100Clear

Purpose: 20 / 20
When to use: 5 / 20
Arguments: 17 / 25
Return value: 15 / 15
Constraints and side effects: 10 / 10
Examples: 10 / 10

Minor
No `required` list, so every argument is optional.no_required

usaspending_get_federal_account

77 / 100Clear

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 25 / 25
Return value: 15 / 15
Constraints and side effects: 7 / 10
Examples: 10 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context

usaspending_get_award

80 / 100Clear

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 25 / 25
Return value: 15 / 15
Constraints and side effects: 10 / 10
Examples: 10 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context

usaspending_get_award_federal_accounts

87 / 100Clear

Purpose: 20 / 20
When to use: 10 / 20
Arguments: 25 / 25
Return value: 15 / 15
Constraints and side effects: 7 / 10
Examples: 10 / 10

No issues.

What static scoring cannot tell

This score reads only the text of each description and schema: it says what is written, not what a model will do. Short tools whose names already say what they do, such as browser_close, score low here even when models use them well, and in our measurements current models chose the right tool in one step even from one-line descriptions, as long as the names and schemas differed. What the text cannot show, such as what happens over several steps and whether an added sentence helps or misleads, is what an evaluation measures, on the Pro and Team plans.

Is your server listed here and you would rather it were not? Email support@forecall.dev, and we will take it off within 7 days.

All scored servers