Skip to main content
Glama

dpyc-oracle

by io.github.lonniev

get_relays

Return the DPYC Nostr relay set, best first.

The single source of truth is dpyc-community/relays.json. An Operator seeds its relay set from here at cold start (its only fixed dependency is this Oracle endpoint), then reads its own bootstrap config from Nostr using just its nsec — no direct GitHub access.

That file is a curated guess: it says which relays are worth using, not which are up this minute. Relays that an operator reported and the Oracle then proved unreachable are moved to the back of the list; everything else keeps its declared order, and nothing is ever dropped.

This call never probes anything — it is on every operator's cold-start path, so it stays a lookup. Ranking improves only when someone hits a dead relay and says so via report_relay_failure. Report failures only; successes need no announcement.

Free.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.6/5.0
Behavior4/5

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

Annotations are absent, so the description carries the full burden manfully: it discloses the call performs no probing, the data is a curated guess not a live status, unreachable relays get moved to the back, and it only reads from a fixed source. It also mentions the cost ('Free'). The only minor gap is no explicit note that it has no side effects or auth requirements, but the description's statements imply it's a pure read.

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?

The description is fairly long for a zero-parameter tool, but it front-loads the core purpose (first sentence) and each subsequent sentence adds meaningful behavioral context (source of truth, no probing, price, feedback loop). It could be trimmed but it's not padded with fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a lookup tool with no parameters, the description fully explains what the result is (ordered relay set), how it's maintained (single source of truth, moved on reports), why it exists (cold-start seeding), and what it does NOT do (probe or guarantee current status). It even ties to the sibling report_relay_failure. Nothing critical is missing.

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?

No parameters exist (0 params, schema coverage 100% trivially), so the baseline is 4. The description adds nothing about parameters because there are none, which is appropriate.

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?

The description states a specific verb and resource: 'Return the DPYC Nostr relay set, best first.' It clearly distinguishes what the tool does (returns a relay set) and its ordering, and mentions the source of truth. It also differentiates from report_relay_failure by explaining it's a lookup, not a report. This is unambiguous and separates it from sibling tools.

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

Usage Guidelines5/5

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

Explicitly positions the tool on the operator cold-start path ('its only fixed dependency is this Oracle endpoint'), says it 'stays a lookup', and tells the agent to use report_relay_failure for reporting dead relays ('Report failures only'). This makes the when/why and the alternative clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All dpyc-oracle toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation4/5

Most tools target a distinct resource or lifecycle step: role-specific registrations, campaign tools, relay tools, and doc/status tools are clearly separated. Minor overlap exists between lookup_member/resolve_service and about/get_rulebook, but the descriptions are detailed enough to route an agent correctly.

Naming Consistency4/5

Almost all tool names use lowercase snake_case with a verb_noun structure (register_*, get_*, list_*, update_*, report_*). A few noun-phrase doc/status tools like about, economic_model, network_advisory, and service_status deviate, but the overall pattern remains readable and predictable.

Tool Count2/5

At 30 tools, this surface is heavy and exceeds the 25-tool threshold, especially for what is mostly a registry/oracle service. Several tools are explicitly not yet implemented, and the count would benefit from deferring those stubs or consolidating related doc/resolution tools.

Completeness3/5

Core areas are covered: member lookup, role registration, operator updates, campaigns, relays, governance docs, and status/advisory queries. However, some workflows are stubs (ban elections, citizen renouncement) and lifecycle gaps remain for authority/advocate updates or deregistration, plus no ban-election status/result tool exists.

Resources