Skip to main content
Glama

Logimu

by com.logimu
OverviewDiscussionsAdmin

batch

Destructive

BATCHES: run any Logimu endpoint over a whole list in one job and come back for the results - the same batch API as REST /v1/batches (see https://api.logimu.com/docs#batch). action=estimate prices a list before anything is billed (free); action=create makes a named, re-runnable batch (add start=true to launch its first run at once); action=run launches a run of an existing batch; action=status reports a batch (runs, line stats) or, with run_id, one run's progress (rows done, credits so far, queue position); action=results returns completed result rows of a run, mid-run too (limit / offset to page; jsonl_url and csv_url give the full download); action=list lists the key's batches; action=schedule repeats a batch daily / weekly / monthly (credit_ceiling, webhook_url); action=delete removes a batch. USE WHEN the user has more than a handful of ASINs, barcodes, search terms, seller ids, brands or seeds to run, wants a daily/weekly refresh, or wants a CSV. Kinds: product (asins or gtins - or source=tracked for the ASINs this key tracks, typically with include [history_only] at 0.05 a row), search (terms, live SERP), seller / brand / category / keywords (paid plans), and every other endpoint as its own kind (shopping, warehouse_search, bestsellers, seller_products, seller_brands, seller_network, brand_sellers, brand_network, keywords_compare, categories, category_search, brands_top, brands_movers, sellers_top, sellers_movers, categories_top) with the endpoint's query parameters in params. Each row bills what the endpoint bills; failed, not-found and duplicate rows are never billed; runs are serialized per marketplace. COST estimate / status / results / list are free; create + run queue billable rows (the estimate is the ceiling). API key required (keyed lanes).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNoestimate / create: product (default), search, seller, brand, category, keywords, or any endpoint kind named in the description.product
modeNoproduct / seller batches: cache = warehouse only, live = scrape every row, auto = warehouse when fresh enough (required on create for product batches).
nameNocreate: the batch's name (1-120 characters).
urlsNobestsellers batches: Best Sellers URLs.
asinsNoproduct batches: the ASINs (or Walmart item ids).
gtinsNoproduct batches: barcodes instead of ASINs.
limitNoresults: rows to return (page with offset; the download URLs carry everything).
pagesNosearch batches: pages per term (1-3); ranked-list batches: pages of 25 rows (1-40).
seedsNokeywords / keywords_compare batches: seed terms.
startNocreate: also launch the first run at once.
termsNosearch / shopping / warehouse_search / category_search batches: the queries.
actionYesWhat to do (see the tool description).
brandsNobrand, brand_sellers, brand_network batches.
offsetNoresults: rows to skip.
paramsNoendpoint kinds: the endpoint's query parameters, fixed for every row.
run_idNoFor status (one run's progress) and results.
sourceNoproduct batches: tracked = the ASINs this key tracks on the marketplace instead of a list.
countryNoestimate / create: us, uk, de, ca, au, fr, it, es, jp, mx, br, walmart (search batches Amazon only).us
includeNoExtras: history (seller / brand / category / keywords), reviews, used, offer_history, bsr_history, history_only (product), blocks (search).
batch_idNoFor run / status / results / schedule / delete.
scheduleNoschedule: how often the batch re-runs (none stops the schedule).
seller_idsNoseller, seller_products, seller_brands, seller_network batches.
webhook_urlNoschedule: POSTed on run completion / pause, HMAC-SHA256 signed; the secret is returned once.
category_idsNocategory / categories batches (ids, or root).
max_age_daysNo
credit_ceilingNoschedule: a firing whose fresh estimate exceeds this does not run (email instead); default 2x the estimate.
history_pointsNo
history_sellersNo
schedule_enabledNoschedule: pause without deleting.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations (destructiveHint=true, readOnlyHint=false) by disclosing billing behavior ('failed, not-found and duplicate rows are never billed'), that estimate is free while create/run bill, that runs serialize per marketplace, that an API key is required, and that webhooks are HMAC-SHA256 signed with a one-time secret. This is unusually rich for a mutation tool.

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 core purpose and the action list are front-loaded, and given 8 actions and 29 params most sentences earn their place. It is nonetheless a dense single block with heavy parenthetical nesting, making it harder to scan than a bulleted breakdown would be.

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?

With no output schema, the description still covers returns (result rows, jsonl_url/csv_url downloads, status line stats, queue position), auth requirements, and cost semantics. An agent has everything needed to choose an action and predict the outcome.

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 description coverage is already 90%, so the schema carries most of the burden, but the description adds real meaning: it maps each action= value to its effect, explains source=tracked ('the ASINs this key tracks'), and calls out costs like the 0.05/row history_only case. It does not fully disambiguate every optional param, so it stays just above baseline.

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 with scope: 'run any Logimu endpoint over a whole list in one job' and pins it to the REST /v1/batches API. An agent can immediately distinguish this bulk runner from the single-item siblings (product, search, seller).

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?

'USE WHEN the user has more than a handful of ASINs... wants a daily/weekly refresh, or wants a CSV' gives a concrete threshold that implicitly separates it from single-item calls. However, it never names a sibling tool as the alternative for the under-threshold case, so routing is inferred rather than stated.

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

All Logimu toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources