get_collection
52 / 100Cloudy
- Purpose
- 17 / 20
- When to use
- 5 / 20
- Arguments
- 18 / 25
- Return value
- 0 / 15
- Constraints and side effects
- 7 / 10
- Examples
- 5 / 10
- MinorSays nothing about what it returns.
no_return_info
https://agents.releases.sh/mcpv2Scores, issues and names only
This page shows how Release Notes Index (sh.releases/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.
instructions_missing52 / 100Cloudy
no_return_info54 / 100Cloudy
no_return_info55 / 100Cloudy
no_usage_contextno_return_info55 / 100Cloudy
no_usage_contextno_requiredno_return_info55 / 100Cloudy
no_usage_contextno_requiredno_return_info57 / 100Cloudy
no_requiredno_return_info59 / 100Cloudy
no_usage_context62 / 100Cloudy
No issues.
62 / 100Cloudy
no_requiredno_return_info62 / 100Cloudy
No issues.
63 / 100Cloudy
no_return_info67 / 100Cloudy
No issues.
68 / 100Cloudy
no_required68 / 100Cloudy
no_return_info69 / 100Cloudy
no_required73 / 100Clear
loose_string_param75 / 100Clear
No issues.
83 / 100Clear
param_no_descriptionThis 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