Skip to main content
Glama

OpenChainBench

by io.github.Flotapponnier

Run a PromQL query (scoped to benchmark metric namespaces)

query_prom

Direct PromQL passthrough for advanced questions that don't map cleanly to list_benchmarks / get_benchmark, e.g. "what was Mobula's p50 head-lag yesterday at 14:00 UTC" or "plot bridge fees over the last hour".

Prefer the higher-level tools first; reach for this when you need: • a custom time window (instant query at a specific point, or range) • a derived metric (rates, ratios, deltas) • a histogram bucket aggregation across chains/regions

Allowed metric namespaces (one prefix per OCB bench family): head_lag_seconds (aggregator latency) bridge_quote_latency_ms*, bridge_cost*, bridge_fees*, bridge_fix_fee*, bridge_gas*, bridge_output*, bridge_estimated_time*, bridge_quote_success l1_finality_*, l2_block_time_* metadata_coverage_*, metadata_api_latency_*, network_coverage_*, networks_supported, wallet_labels_* perp_fees_*, perp_funding_*, perp_venue_*, perp_execution_*, perp_liq_*, perp_realized_vol_*, ocb_buyback_*, ocb_oracle_*, ocb_validator_*, ocb_chain_* gas_error_*, gas_predicted_*, gas_realized_*, gas_oracle_* peg_* (stablecoin peg, both variants) solana_landing_* (TX landing observational + active) rpc_latency_*, rpc_call_total, rpc_health, rpc_archive_depth_supported relay_*, per_swap_margin_usd (bridge revenue) Queries referencing other metrics (operational/internal ones like up, scrape_*, process_*, go_*, wallet_balance_* or any label- enumeration shape) are refused with {error, reason}.

Example: instant p50 over 1h for Mobula head-lag on Base: query_prom({ query: "quantile_over_time(0.5, head_lag_seconds{aggregator="mobula",chain="base"}[1h]) * 1000" })

Example: 7-day sparkline of average bridge fees: query_prom({ query: "avg_over_time(bridge_fees_percent[1d])", windowSec: 604800, steps: 168 })

Returns: { query, value } for instant queries, { query, windowSec, series } for range.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesPromQL expression referencing published benchmark metric prefixes only. Function names, label keys, and quoted label values are fine; bare metric names must be allowlisted.
stepsNoNumber of samples for a range query (2 to 360). Default 60. Step duration = windowSec / steps.
windowSecNoIf set, run a range query over the last N seconds (max 7 days = 604800). Omit for an instant query.

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations provided, the description fully discloses behavior: allowed metric namespaces are exhaustively listed, non-allowed queries are refused with error details, return format is explained for both instant and range queries, and default steps value is mentioned. No gaps in transparency.

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?

Well structured with clear sections and bullet lists. Examples are helpful. A bit long, but each part adds necessary information. Could be slightly tightened by removing the namespace repetition from the query parameter description, but overall efficient.

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 tool with 3 parameters, no output schema, and complexity in allowed queries, the description is comprehensive. It covers purpose, usage guidance, allowed and disallowed queries, error behavior, return format, and parameter relationships. An agent can confidently select and invoke this tool.

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 baseline is 3. The description adds significant value beyond the schema: explains allowed namespaces for the query parameter, gives the relationship between windowSec and steps, and provides concrete examples. This is more than minimal but not exhaustive (e.g., no format details for label values).

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 it is a 'Direct PromQL passthrough' for advanced questions not handled by sibling tools `list_benchmarks` and `get_benchmark`. It specifies it is scoped to benchmark metric namespaces and gives concrete examples, making the purpose precise and distinct.

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 instructs to 'Prefer the higher-level tools first' and then lists exactly when to use this tool: custom time windows, derived metrics, histogram aggregations. Also states what queries are refused (internal metrics). This provides excellent decision support.

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

All OpenChainBench 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

A4.9/5.0
Disambiguation5/5

Each tool has a clearly distinct role: list_benchmarks for discovery, get_benchmark for detailed citation-ready data, and query_prom for custom PromQL analysis. The descriptions explicitly guide which tool to use, eliminating ambiguity.

Naming Consistency5/5

All tool names follow the same verb_noun snake_case pattern: list_benchmarks, get_benchmark, query_prom. This consistent convention makes the API predictable and easy to reason about.

Tool Count5/5

With three tools, the server is well-scoped for its purpose. Each tool earns its place: listing, retrieving details, and executing advanced queries. No redundant tools exist, and the count is sufficient to cover the domain without being excessive.

Completeness5/5

The tool set fully covers the read-only benchmark domain: enumeration (list_benchmarks), specific retrieval (get_benchmark), and arbitrary custom analysis (query_prom). No obvious gaps like missing search or filter capabilities are apparent, as list_benchmarks provides a flat index.

Resources