Skip to main content
Glama

sb_collection

Destructive

Manage data tables, typed fields, and records; import or export CSV, upsert records by external_id, and edit, move, or remove items by ID.

Instructions

Data tables (collections): tables, typed fields, records, CSV export/import (appends), upsert by external_id. edit merges values (null clears). get/edit/remove/move take id.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "sb_collection"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNorecord
csvNo
idsNoevery id, new order
keyNo
refNoreference target table
nameNotable name / field label
slugNo
sortNokey, -key desc
typeNo
deltaNo
fieldNoid or key
limitNo
actionYes
filterNo{key: value}
offsetNo
valuesNo
dry_runNo
optionsNo
recordsNo
site_idNo
requiredNo
publishedNo
collectionNoid or slug
external_idNo
public_readNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.105.0

TDQS

B3.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the bar is lower, and the description still adds real semantic disclosure beyond them: edit merges rather than replaces, null clears a value, import appends, and upsert matches on external_id. These are exactly the non-obvious mutation traits an agent needs before a destructive write. It stops short of mentioning dry_run (present in the schema), permissions, or limits on the 500-record import cap.

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?

Two tight sentences with no filler, and the resource scope is front-loaded before the per-action caveats. The telegraphic parenthetical style ("(appends)", "(null clears)") is dense but unambiguous and saves space in a description that must cover a lot.

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?

This is a 19-action, 25-parameter destructive multiplexer with no output schema, and the description covers only a fraction of it. An agent still cannot tell from prose which parameters each action consumes, how listing/pagination or export results are returned, or what dry_run does — a significant gap for a tool this complex.

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

Parameters2/5

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

Schema description coverage is only 32% across 25 parameters, so the description must compensate and largely does not. It clarifies id ("get/edit/remove/move take id") and ties upsert to external_id, but leaves key vs field vs slug vs ref, options, delta, dry_run, published, public_read, and the filter/sort/limit/offset paging set unexplained in both schema and prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource domain concretely — data tables/collections with typed fields, records, and CSV export/import — so an agent knows roughly what territory this tool covers. But it never states the overall verb or that this is a single multiplexed tool spanning 19 actions (list, create, field_add, records, export, import, upsert...), and gives no differentiation from siblings such as sb_add, sb_set, or sb_remove, which sound like they could overlap.

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

Usage Guidelines3/5

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

Useful per-action rules are buried in the text: import appends rather than replaces, upsert keys on external_id, and get/edit/remove/move require an id. That is genuine usage information, but there is no statement of when to pick this tool over the many sibling tools, no prerequisites, and no exclusions for the other 14 actions.

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