Untap: tool descriptions scored io.github.aneduaim/untap-mcp

tools/list taken: 2026-11-02 (UTC)
From: Official MCP Registry
Connected to: https://untap.money/api/mcp
Homepage: untap.money/connect
Repository: github.com/aneduaim/untap-mcp
Scoring rules: v2
Removal: support@forecall.dev

Scores, issues and names only

This page shows how Untap (io.github.aneduaim/untap-mcp)'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.aneduaim/untap-mcp

Average score: 62.8 / 100Cloudy
Tools: 20
Near-identical descriptions: 0

Across the server

Minor
The server's instructions are 2838 characters. Claude Code reads only the first 2,048 by default (Codex 0.154.0 reads them whole). Put what the server is for first.instructions_long

Tools

list_commutes

48 / 100Cloudy

Purpose: 14 / 20
When to use: 5 / 20
Arguments: 22 / 25
Return value: 0 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

Minor
No `required` list, so every argument is optional.no_required
Minor
Says nothing about what it returns.no_return_info

list_my_claims

51 / 100Cloudy

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

Minor
No `required` list, so every argument is optional.no_required
Minor
Says nothing about what it returns.no_return_info

list_savings

54 / 100Cloudy

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

Minor
Says nothing about what it returns.no_return_info

stop_commute

54 / 100Cloudy

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

Minor
Says nothing about what it returns.no_return_info
Minor
Required identifiers whose description does not say where the value comes from: commute_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

check_tfl_journeys

56 / 100Cloudy

Purpose: 17 / 20
When to use: 0 / 20
Arguments: 22 / 25
Return value: 7 / 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

delete_my_data

58 / 100Cloudy

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

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

add_tfl_journeys

59 / 100Cloudy

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

Minor
Says nothing about what it returns.no_return_info

save_commute

59 / 100Cloudy

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

Minor
Says nothing about what it returns.no_return_info

add_parking_fine

62 / 100Cloudy

Purpose: 17 / 20
When to use: 5 / 20
Arguments: 21 / 25
Return value: 7 / 15
Constraints and side effects: 7 / 10
Examples: 5 / 10

No issues.

scan_for_claims

64 / 100Cloudy

Purpose: 17 / 20
When to use: 0 / 20
Arguments: 25 / 25
Return value: 7 / 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

update_claim_status

64 / 100Cloudy

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

Minor
Says nothing about what it returns.no_return_info
Minor
Required identifiers whose description does not say where the value comes from: claim_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

check_flight_compensation

66 / 100Cloudy

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

No issues.

find_money_owed

66 / 100Cloudy

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

No issues.

get_delay_repay_rules

66 / 100Cloudy

Purpose: 17 / 20
When to use: 0 / 20
Arguments: 25 / 25
Return value: 7 / 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

add_flight

68 / 100Cloudy

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

No issues.

add_train_journey

69 / 100Cloudy

Purpose: 17 / 20
When to use: 10 / 20
Arguments: 23 / 25
Return value: 7 / 15
Constraints and side effects: 7 / 10
Examples: 5 / 10

No issues.

check_commute

71 / 100Clear

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

Minor
Required identifiers whose description does not say where the value comes from: commute_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

save_claim

71 / 100Clear

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

No issues.

check_train_delay

74 / 100Clear

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

No issues.

get_claim_instructions

76 / 100Clear

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