Skip to main content
Glama
rzazo24

nostrclaw

by rzazo24
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Trust score for keys

trust_score
Read-onlyIdempotent

Score Nostr keys by analyzing network vouching: follower counts, trusted key proximity, interactions, and age. Identify new or existing keys.

Instructions

Scores how much the network vouches for keys, using what the configured relays hold about who follows whom: how many keys follow it, how many of those followers are themselves followed (established), how close it is to keys YOU trust (pass them as trusted: a trusted key following it counts most), how many different keys interacted with it, and how long it has been seen. Give pubkeys, or leave them out to examine the NEW keys of a recent window (keys not seen on any relay before it). A web-of-trust aid, not a verdict or an identity check: keys can follow each other in rings, and "unknown" means nothing vouches for it here, not that it is bad.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
relaysNoRelays to read from; each must be configured. Default: all configured. The first one is where new keys are looked for.
pubkeysNoKeys to score (hex or npub). Omit to take the new keys of the last `recentHours` seen on the FIRST relay and not seen before on any of the relays.
trustedNoKeys you trust (hex or npub), e.g. your own. Without them the "close to a trusted key" points are not available.
recentHoursNoWhen no pubkeys are given: the window in which a key must have appeared for the first time (default 48).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.14.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint, so the safety profile is covered. The description adds real context beyond that: the caveat that rings can form, that 'unknown' means nothing vouches for it here rather than 'bad', and that it is an aid not a verdict. It stops short of describing return shape or latency/cost of querying many relays.

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?

Front-loaded with the core purpose before the scoring breakdown and caveats. The long middle sentence listing the five signals is dense but every clause earns its place; nothing is redundant filler.

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?

For a read-only tool with no output schema, the description explains inputs, defaults, and the semantics of an 'unknown' result. It does not describe the return format or score range, which is the main remaining gap given there is no output schema to fall back on.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description goes beyond the schema by explaining the scoring weight of `trusted` ('a trusted key following it counts most') and reinforcing the omit-`pubkeys` behavior, adding interpretation the schema alone does not provide.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Scores how much the network vouches for keys') and then enumerates the exact signals used, so the agent knows precisely what the tool computes. It is clearly distinct from siblings like account_triage or author_report.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly covers the two invocation modes: pass `pubkeys` to score given keys, or omit them to examine the NEW keys of a recent window, and explains the role of `trusted`. It gives clear operating context but never names an alternative sibling tool for adjacent questions.

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