Cockatoo

update_site

DestructiveIdempotent

Change only some fields of the draft, using the current revision. changes is a JSON Merge Patch over the SiteDocument: objects merge, null removes a field, and arrays (services, gallery, pages, sections) are replaced whole. Does not change the live publication.

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": {
      "revision": "<revision>",
      "changes": "<changes>"
    },
    "name": "update_site"
  }
}

Input Schema

Name	Required	Description
`changes`	Yes	Only the fields to change, e.g. {"phone":"0400 000 000","hours":"Mon–Fri 8–5"}
`revision`	Yes
`idempotencyKey`	No	Optional. Set a random key and reuse it exactly when retrying, so a retry is not applied twice

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 29, 2026

changedInput schema / properties / idempotencyKey / description

Previous value: -"Unique random key for this operation; reuse exactly when retrying"New value: +"Optional. Set a random key and reuse it exactly when retrying, so a retry is not applied twice"

changedInput schema / required

Previous value: -[
-  "revision",
-  "changes",
-  "idempotencyKey"
-]New value: +[
+  "revision",
+  "changes"
+]

AddedOct 29, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Beyond the annotations it explains exactly what the destructive semantics mean: objects merge, null removes a field, and arrays (services, gallery, pages, sections) are replaced whole. It also scopes the blast radius ('Does not change the live publication') and ties the call to optimistic concurrency via 'using the current revision', which the annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the partial-update premise, then the merge semantics, then the safety boundary. No filler and each sentence carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a high-risk mutation with no output schema and no annotations covering merge semantics, the description supplies the critical behavioral detail an agent needs. Minor gaps remain: revision-conflict behavior, permissions, and whether the returned revision must be re-read after the call.

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 coverage is 67% and the description adds genuine meaning for `changes`, spelling out merge-patch rules that the schema only gestures at with an example. `revision` is given purpose (current-revision concurrency) but the failure behavior on mismatch is not described, and `idempotencyKey` is only covered by the schema.

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?

States a specific verb and resource ('Change only some fields of the draft') and pairs it with a concrete mechanism (JSON Merge Patch over SiteDocument). It implicitly separates itself from whole-document saves and publication tools by stressing 'only some fields' and 'Does not change the live publication', though it never names the sibling it contrasts with.

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?

Usage is implied rather than stated: a reader infers this is for partial edits of a draft and that revision must match. There is no explicit guidance on when to pick this over save_site/publish_site or what to do on a revision conflict, leaving the agent to infer the workflow.

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

All Cockatoo tools Inspect

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

Need Help?