Skip to main content
Glama

Kirk — Unsupervised Structural Change Detection

by io.github.UlyssesModel

Score Batch of Order Books

kirk_score_book_batch
Read-only

Score up to 500 L2 order-book snapshots in one MCP call — returns an entropies list plus engine attestation.

Purpose: Batch-score up to 500 snapshots through the sealed engine in a single MCP dispatch.

Use when: You are validating batch behaviour, comparing entropy distributions across small book sets, or running interactive experiments up to 500 books at a time.

Do not use when: You have more than 500 books, or you are looping this tool from an LLM. Batches >500 raise a structured batch_too_large before any ledger debit. For sustained bulk work, call kirk_bulk_howto — the stdlib Python client scores at zero LLM tokens per iteration.

Capability class(es):

  • C2 (variable-universe cross-section entropy — heterogeneous batch shapes are handled by one model without retraining).

  • C5 (sealed engine sha stamped on every response).

  • C6 (bit-exact reproducibility across substrates and runs).

Path fit: Validation via MCP (this tool). Production bulk workloads run in-process under sealed-engine attestation — same binary sha as this endpoint. Contact Kavara for deployment options. The MCP round-trip is inappropriate for high-throughput consumption.

Cost: 1 IU per 50 books (minimum 1 IU per call). n≤50 → 1 IU; n=51..100 → 2 IU; a full 500-book batch → 10 IU. Validation tier — validation-scale limits. LLM-agent-scoped cap at 500 books; use kirk_bulk_howto for anything larger.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
booksYeslist of book dicts (bid_px, ask_px, sizes...). Max 500 per call — larger batches raise a structured `batch_too_large` error pointing at kirk_bulk_howto.
model_idNoregistered model_id (see kirk_list_models).kirk-test1-binary-threshold-v1

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Even though annotations already mark readOnlyHint=true and destructiveHint=false, the description adds substantial behavioral context: cost formula per 50 books, the exact error behavior for batches >500 ('batch_too_large' before any ledger debit), sealed-engine attestation, and reproducibility guarantees. No contradiction with annotations.

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 longer than typical (about 200 words) but well-structured with clear headings (Purpose, Use when, Do not use when, Capability classes, Path fit, Cost). The main purpose is front-loaded in the first sentence. Each section earns its place given the tool's complexity, though some parts like 'Path fit' could be trimmed for an MCP tool.

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?

The tool has an output schema, so return values need not be detailed, but the description covers limits, cost, error handling, alternatives, and reproducibility. It is fully sufficient for an agent to select and invoke the tool correctly, even with the rich set of sibling tools.

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 description coverage is 100%, so the baseline is 3. The description adds some context around the 'books' parameter (e.g., max 500 and cost implications) but the schema already documents the list format and the batch_too_large error. No significant extra parameter-level meaning beyond what the schema provides.

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 opens with a specific verb and resource: 'Score up to 500 L2 order-book snapshots in one MCP call — returns an entropies list plus engine attestation.' This clearly states what the tool does and its scope (batch of up to 500), distinguishing it from siblings like kirk_score_book (single) and kirk_bulk_howto (bulk).

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?

Explicit 'Use when' and 'Do not use when' sections provide clear context. The description names alternatives: kirk_bulk_howto for sustained bulk work, and notes the 500-book limit. This is textbook guidance on when to use this tool versus others.

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

All Kirk — Unsupervised Structural Change Detection 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

A4.7/5.0
Disambiguation5/5

Every tool has a clearly distinct purpose: billing (checkout/show/usage), scoring (single/batch/legacy/synthetic/random), utility (health/models/bulk_howto/render/research). Descriptions are detailed enough to prevent confusion.

Naming Consistency5/5

All tools follow a consistent 'kirk_<domain>_<verb>' pattern (e.g., kirk_billing_checkout, kirk_score_book). No mixing of conventions or unpredictable names.

Tool Count5/5

12 tools is well within the optimal range. Each tool serves a specific need without redundancy, covering scoring, billing, health, models, and research.

Completeness5/5

The tool surface covers the full workflow: scoring (single/batch/legacy/synthetic/research), billing (checkout/balance/usage), health checking, model listing, tensor prep, and bulk client generation. No obvious gaps for the intended domain.

Resources