Typebar (formerly SuperDocs)

approve_change

Decide changes held for review (chat or chat_async). Single: change_id + approved=true|false (+ optional feedback for the AI to revise on). Batch: a 'changes' array of per-change decisions. Approved changes apply atomically; denied ones are discarded. When a decision completes the batch (batch_complete=true), the job resumes and this call waits until the resumed turn settles, then returns job_status and applied: applied=true means the approved changes are in the document (an export or the next chat includes them); job_status awaiting_approval means the turn proposed more changes (decide them the same way); failed means they were not applied. With wait_for_result=false it returns at once (applied=false) and you wait with get_job.

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": {
      "session_id": "<session_id>",
      "job_id": "<job_id>",
      "approved": "<approved>"
    },
    "name": "approve_change"
  }
}

Input Schema

Name	Required	Description
`job_id`	Yes	Job ID that is awaiting approval.
`changes`	No	Batch decisions: array of {change_id, approved, feedback}. Each listed change_id with approved=true is an explicit decision and applies, including changes flagged for individual review; an approve that names no change decides nothing and returns the flagged ids in needs_individual_approval.
`approved`	Yes	Whether to approve (true) or deny (false) the change.
`feedback`	No	Optional feedback explaining why a change was denied. Helps the AI adjust future suggestions.
`change_id`	No	Specific change to approve/deny (for individual decisions). Get change IDs from the job's pending_changes.
`session_id`	Yes
`wait_for_result`	No	Default true: when the decision completes the batch, the call returns after the resumed turn settles (changes applied and saved, a new review pause, or a failure), reported in job_status, applied and job. false returns once the decision is recorded (applied=false, job_status='in_progress'); then wait with get_job.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 2, 2026

removedInput schema / properties / authorization

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "title": "Authorization"
-}

changedInput schema / properties / changes / description

Previous value: -"Batch decisions: array of {change_id, approved, feedback} objects. Use for 'Accept All' or 'Deny All'. A change whose machine_checks.requires_individual_confirmation is true is never approved by a multi-change batch: it stays pending (named in needs_individual_approval) until you approve it on its own change_id."New value: +"Batch decisions: array of {change_id, approved, feedback}. Each listed change_id with approved=true is an explicit decision and applies, including changes flagged for individual review; an approve that names no change decides nothing and returns the flagged ids in needs_individual_approval."

addedInput schema / properties / wait_for_result

Added value: +{
+  "default": true,
+  "description": "Default true: when the decision completes the batch, the call returns after the resumed turn settles (changes applied and saved, a new review pause, or a failure), reported in job_status, applied and job. false returns once the decision is recorded (applied=false, job_status='in_progress'); then wait with get_job.",
+  "title": "Wait For Result",
+  "type": "boolean"
+}

Changed1 schema field changedNov 1, 2026

changedInput schema / properties / changes / description

Previous value: -"Batch decisions: array of {change_id, approved, feedback} objects. Use for 'Accept All' or 'Deny All'."New value: +"Batch decisions: array of {change_id, approved, feedback} objects. Use for 'Accept All' or 'Deny All'. A change whose machine_checks.requires_individual_confirmation is true is never approved by a multi-change batch: it stays pending (named in needs_individual_approval) until you approve it on its own change_id."

First observedOct 21, 2026

TDQS

A4.8/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so: atomic application of approved changes, silent discard of denied ones, blocking vs non-blocking behavior, and the meaning of applied/job_status (applied=true means changes are in the document and will appear in an export or next chat). It also discloses the wait-until-turn-settles side effect that a caller would otherwise not anticipate.

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-loads the core verb and mode split before the state machine detail, and every clause is load-bearing. It is a dense block of prose with heavy parenthetical nesting, which makes it slightly harder to scan than it needs to 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?

No output schema exists, and the description compensates by documenting the returned job_status values and the applied flag, plus what happens to the job on batch completion. For a 7-parameter, no-annotation mutation tool, nothing essential is missing.

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 already 86%, so the schema does most of the work, but the description adds real semantics: the batch array's per-change decision shape, that feedback exists 'for the AI to revise on', and the exact behavior of wait_for_result=true vs false including the resulting job_status values. Only marginal overlap keeps it from a 5.

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 ('Decide changes held for review') and immediately names the two origin flows (chat, chat_async). It also splits the two invocation modes (single via change_id + approved, batch via a 'changes' array), so an agent can tell exactly which shape it needs.

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 contrasts single vs batch usage and names the alternative path: with wait_for_result=false 'you wait with get_job'. It also tells the agent what to do on each terminal state (awaiting_approval means decide the newly proposed changes the same way).

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

All Typebar (formerly SuperDocs) 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.