Cloche

List records

list_records

Read-only

Reads an app's data as the person this call acts for. With a collection named, lists one page of its records: all of a shared collection, only their own of a private one. Takes the previous page's next_cursor, and returns records and next_cursor, empty on the last page. With no collection, returns the collections the app declares, each shared or private with its fields and their types. Field values are written by the app's users.

Input Schema

TableJSON Schema

Name	Required	Description
`app_id`	Yes	the app, as list_apps gave it
`cursor`	No	the previous page's next_cursor; omit for the first page
`collection`	No	a collection the app declares; omit to get the app's collections instead of records

Output Schema

TableJSON Schema

Name	Required	Description
`records`	Yes	one page of records the person may read, when a collection was named; empty otherwise
`collections`	Yes	the collections the app declares, when no collection was named; empty otherwise
`next_cursor`	Yes	the cursor for the next page, empty on the last

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 11, 2026

addedOutput schema / properties / records / items / properties / created_by

Added value: +{
+  "description": "the account that wrote the record, in the form user.id takes. Absent when someone wrote it through a share link without signing in, when the platform wrote it, and when the person cannot see who is in the app",
+  "type": [
+    "null",
+    "string"
+  ]
+}

addedOutput schema / properties / records / items / properties / updated_by

Added value: +{
+  "description": "the account that last changed the record. Absent when that is not known",
+  "type": [
+    "null",
+    "string"
+  ]
+}

AddedOct 8, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: results are scoped to the acting person, private collections show only their own records, pagination terminates with an empty next_cursor, and field values are user-authored.

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?

Three tightly packed sentences with the primary read behavior front-loaded and pagination and collection-mode details following in logical order. Slightly dense—the collection-mode clause is a long second sentence—but nothing is wasteful.

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 paginated read tool with an existing output schema and full annotation coverage, the description covers everything the agent needs: actor scoping, the two operating modes, pagination continuation, and terminal-page behavior. Return values need not be expanded since an output schema exists.

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% and the schema already explains app_id, cursor and collection individually. The description's contribution is mainly restating the mode-switch semantics of collection and cursor, which is mildly useful but largely duplicative of the schema text, so the baseline 3 applies.

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

Purpose4/5

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

The description names a specific verb and resource (reads an app's data, lists one page of records) and precisely defines scope via the actor ('as the person this call acts for') and the shared/private visibility rule. It distinguishes itself clearly from write siblings like save_record, but never names an alternative tool to steer selection, which keeps it just short of a 5.

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?

It gives clear conditional guidance: supply a collection to get records, omit it to get the app's declared collections, and pass the previous page's next_cursor to continue. What's missing is any explicit when-not or a pointer to a sibling for adjacent tasks.

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

All Cloche tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.