Total CMS

query_collection

Read-onlyIdempotent

Query a collection for paginated content. Returns the matching items plus pagination metadata (total, limit, offset, has_more); each item is decorated with a public url field where one is configured. Use REST-style include / exclude filter strings (comma-separated field:value pairs; AND-semantics for include, OR-semantics for exclude) and sort (e.g. date:desc). Only properties listed in the catalog below are queryable — other schema properties exist on objects but are not filterable here; use get_object if you need the full record or describe_collection to see every property. This tool does not free-text search content — use search_collection for that. It does not fetch a single object by id — use get_object.

Available collections and filterable properties:

articles — id (id, sortable), title (text), author (select), summary (textarea), date (date, sortable), draft (toggle), updated (datetime, sortable)
comparisons — competitor (text), competitorUrl (url), heading (text), lede (textarea), reviewed (date, sortable), draft (toggle), sort (number, sortable), id (id, sortable)
extension — id (id, sortable), name (text), extensionId (text), soldAs (text), summary (textarea), category (select), price (number, sortable), currency (select), minEdition (select), minVersion (text), bundled (toggle), beta (toggle), docsUrl (url), productUrl (url), draft (toggle), owner (select), featured (toggle), approved (datetime, sortable), submitted (datetime, sortable), weight (range, sortable)
guides — heading (text), lede (textarea), reviewed (date, sortable), draft (toggle), sort (number, sortable), id (id, sortable), kind (select), product (select)
releases — id (id, sortable), version (text), title (text), date (date, sortable), draft (toggle), urgent (toggle), fullnotesurl (url), announce (toggle)
showcase — name (text), url (url), industry (select), id (id, sortable), owner (select), draft (toggle), featured (toggle), approved (datetime, sortable), submitted (datetime, sortable), weight (range, sortable)
starters — id (id, sortable), name (text), job (text), useCase (select), siteName (text), summary (textarea), status (select), package (text), buildCommand (text), coreStarter (select), minEdition (select), minVersion (text), demoUrl (url), repoUrl (url), featured (toggle), draft (toggle), updated (datetime, sortable)
streams — id (id, sortable), title (text), date (date, sortable), summary (textarea), release (select), draft (toggle)
studio-app — id (id, sortable), summary (textarea)

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": {
      "collection": "<collection>"
    },
    "name": "query_collection"
  }
}

Input Schema

Name	Required	Description	Default
`sort`	No	Sort rule "field:direction"; multiple rules comma-separated. Only fields marked sortable in the catalog will sort.
`limit`	No	Maximum items to return. Capped at 50 (vs. REST's 100) to fit MCP response-size budgets.
`format`	No	Rendered format for content fields. Accepted now for forward-compat; full conversion ships with the Tiptap→markdown converter in a later release.	markdown
`locale`	No	BCP 47 locale tag. Accepted for forward-compat with the 3.6 i18n release — has no effect today.
`offset`	No	Number of items to skip — combine with limit for pagination.
`exclude`	No	Comma-separated field:value pairs that exclude items (OR). Drafts the caller may not see are removed before this filter runs, whatever it says.
`include`	No	Comma-separated field:value pairs items must ALL match. Wildcards "foo", "foo", "foo" supported.
`collection`	Yes	Collection id (slug-form). Use list_collections to discover available collections.

Output Schema

Name	Required	Description
`items`	Yes	Matching objects in sort order. Field set varies by collection — call describe_collection for the schema.
`limit`	Yes	Cap applied to this response — server may have lowered the requested limit.
`total`	Yes	Total matching items (post-persona-filter).
`offset`	Yes
`has_more`	Yes	True when total > offset + count(items); call again with offset += limit to paginate.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 24, 2026

TDQS

A4.5/5.0

Behavior3/5

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

Annotations already declare readOnly/idempotent/non-destructive/non-open-world, so the safety profile is covered. The description still adds real behavioral context: pagination metadata fields returned, a public `url` decoration on items, AND-semantics for include vs OR-semantics for exclude, drafts being stripped before the exclude filter runs, and the 50-vs-100 limit cap. The gaps are the forward-compat params: `format` and `locale` are documented in the schema as no-ops but the description never warns that rendered format will not actually be honored.

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?

Front-loaded correctly: what it does, then what it returns, then what it is not, then the reference catalog. The catalog is long and context-heavy, but each collection line carries filterable-field data an agent genuinely needs; a minor tightening would be collapsing the routing sentences that repeat the get_object mention twice.

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 read-only query tool with a full output schema, the description covers purpose, alternatives, filter syntax, sortable fields, pagination, and permission-filtered drafts. Nothing material to correct invocation is left out, and return values are correctly left to the output schema rather than restated at length.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline would be 3, but the description earns more by supplying the queryable-property catalog per collection with type and sortable markers — information that exists nowhere in the schema and directly determines whether include/exclude/sort will silently fail. It also spells out the `field:value` syntax, wildcard forms, and sort direction convention.

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 first sentence names a specific verb and resource ("Query a collection"), states the scoping ("paginated content"), and the very next clause enumerates the return shape. It actively carves out boundaries against search_collection and get_object, so an agent can distinguish it from siblings without opening a schema.

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 states two negative cases with the correct alternative named in each: no free-text search (use search_collection) and no single-object fetch (use get_object), plus routing to describe_collection for full property listings. The per-collection catalog tells the caller up front which filters and sorts are legal, which is the main failure mode for this tool.

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

All Total CMS tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.