peerlytics

get_leaderboard

Maker/taker leaderboard. Without params: cumulative leaderboard backed by MakerStats/TakerStats. With from/to/range: per-window indexer compute. Hard cap: 400-day window.

Input Schema

TableJSON Schema

Name	Required	Description
`to`	No	Window upper bound (exclusive). ISO-8601 or unix-seconds. Defaults to `now` when omitted but `from` is supplied.
`from`	No	Window lower bound (inclusive). ISO-8601 (`2026-04-01T00:00:00Z`) or unix-seconds. Optional when `range` is supplied.
`limit`	No	Max results per list (default: 20, max: 100).
`range`	No	Unified date-range shortcut shared across analytics + explorer endpoints. Hard cap: 400-day window. When set, takes precedence over `from`/`to`. Legacy values (`3mtd`, `q1`-`q4`, `custom`) were retired on 2026-04-30; use the explicit shortcuts below.
`cursor`	No	Pass the previous page's `next_cursor` to walk forward without offset drift. This is the supported pagination path on every list endpoint.
`offset`	No	Deprecated. Use `cursor` instead — offset pagination is fragile under concurrent writes and slow at scale. Still accepted for backwards compatibility while integrators migrate.

TDQS

B3.4/5.0

Behavior3/5

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

No annotations provided, so description bears full burden. It explains the two computational modes and a hard cap on the window, but does not mention response structure, pagination behavior, or any authentication or rate limit considerations. Adequate but not comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: two sentences plus a note. No wasted words, key information front-loaded. Every sentence adds value.

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

Completeness2/5

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

Tool has 6 parameters and no output schema, but description omits response structure (e.g., leaderboard entries, fields, pagination cursors). For a list endpoint, this is a significant gap that hinders agent understanding of what the tool returns.

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

Parameters3/5

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

Schema coverage is 100%, so baseline is 3. The description adds minimal extra meaning beyond the schema, merely grouping from/to/range as triggers for per-window mode. Key details like range precedence are already in the schema.

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 clearly states the tool returns a maker/taker leaderboard and distinguishes two modes (cumulative vs per-window) based on parameters. The name 'get_leaderboard' combined with the description makes the purpose unambiguous and distinct 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 Guidelines2/5

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

No explicit guidance on when to use this tool vs sibling tools like get_maker or get_taker. The description only differentiates between parameter modes within the tool itself, not external alternatives.

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

All peerlytics tools Inspect

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

C2.8/5.0

Disambiguation3/5

Most get_* and list_* tools target distinct domain entities, but several high-level analytics endpoints overlap in purpose (get_analytics_summary, get_protocol_overview, get_market_summary, get_timeseries, get_leaderboard), and pairs like get_deposit/get_deposit_context and get_vault/get_vault_analytics create close boundaries. The descriptions clarify the differences, but an agent would need to read carefully to avoid misselection.

Naming Consistency5/5

The tool set follows a strong verb_noun pattern: get_ for single-entity or detail views, list_ for collections, plus explicit action endpoints like export_trade_log, plan_routes, and search_explorer. All names are snake_case and predictable, with no mixing of conventions.

Tool Count3/5

28 tools is on the heavy side for an MCP server, even for a broad analytics domain. Most tools map to real entities, but the surface is padded by overlapping summary/analytics endpoints and separate detail, context, and analytics variants for the same resources.

Completeness4/5

The server provides broad read-only coverage of the protocol domain: deposits, intents, makers, takers, vaults, delegates, verifiers, platforms, integrators, orderbook, routes, activity, and search. Minor gaps such as no list_vaults or list_integrators are workable via search/get endpoints, and mutating operations appear out of scope for an analytics-focused server.

Resources

Need Help?