Memory: tool descriptions scored

tools/list taken: 2026-09-30 (UTC)
From: npm @modelcontextprotocol/server-memory@0.6.3
Homepage: github.com
Scoring rules: v2

Scores, issues and names only

This page shows how Memory'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.

A server with a public URL can be scored as it is today: score from a URL

servers/memory

Average score: 43.8 / 100Cloudy
Tools: 9
Near-identical descriptions: 1

Across the server

Minor
The server has no instructions. Say there, once, what the server is for and when to use it: Claude Code and Gemini CLI read the instructions before the tool descriptions.instructions_missing

Tools whose descriptions are nearly the same

1 of 1 pairs shown, highest description similarity first.
Tool	Tool	Description similarity	Name similarity
delete_entities	delete_relations	0.62	0.33

Tools

delete_observations

34 / 100Rain

Purpose: 6 / 20
When to use: 0 / 20
Arguments: 13 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

Major
The description only restates the name (9 words).restates_name
Major
Says nothing about when to use it, or when not to.no_usage_context
Minor
Arguments without a description: deletions.param_no_description
Minor
The description mentions none of its 3 or more arguments.params_not_in_description

create_entities

35 / 100Rain

Purpose: 6 / 20
When to use: 0 / 20
Arguments: 14 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

Major
The description only restates the name (8 words).restates_name
Major
Says nothing about when to use it, or when not to.no_usage_context
Minor
Arguments without a description: entities.param_no_description

delete_relations

39 / 100Rain

Purpose: 6 / 20
When to use: 0 / 20
Arguments: 18 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

Major
The description only restates the name (7 words).restates_name
Major
The description is too short (7 words).too_short
Major
Says nothing about when to use it, or when not to.no_usage_context
Minor
Its description is nearly the same as delete_entities's (similarity 0.62); only the names and schemas tell them apart. Say in this description when to use delete_entities instead.confusable_pair

add_observations

41 / 100Cloudy

Purpose: 13 / 20
When to use: 0 / 20
Arguments: 13 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Minor
Arguments without a description: observations.param_no_description

read_graph

46 / 100Cloudy

Purpose: 6 / 20
When to use: 0 / 20
Arguments: 25 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

Major
The description only restates the name (5 words).restates_name
Major
The description is too short (5 words).too_short
Major
Says nothing about when to use it, or when not to.no_usage_context

search_nodes

46 / 100Cloudy

Purpose: 13 / 20
When to use: 0 / 20
Arguments: 18 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

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

create_relations

51 / 100Cloudy

Purpose: 17 / 20
When to use: 5 / 20
Arguments: 14 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

Minor
Arguments without a description: relations.param_no_description

delete_entities

51 / 100Cloudy

Purpose: 13 / 20
When to use: 0 / 20
Arguments: 23 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Minor
Its description is nearly the same as delete_relations's (similarity 0.62); only the names and schemas tell them apart. Say in this description when to use delete_relations instead.confusable_pair

open_nodes

51 / 100Cloudy

Purpose: 13 / 20
When to use: 0 / 20
Arguments: 23 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

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

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