GetMattered

Prepare Applications Again

getmattered_reprepare_applications

Destructive

Builds the documents and form answers of applications again. Nothing is sent. Uses AI credits.

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": {
      "application_ids": "<application_ids>"
    },
    "name": "getmattered_reprepare_applications"
  }
}

Input Schema

Name	Required	Description	Default
`steps`	No	The preparation steps to run again. Left out, every step that is out of date runs.
`application_ids`	Yes	Application ids to act on, 1 to 25 (e.g. [1550, 1551]), from getmattered_get_applications

Output Schema

Name	Required	Description
`results`	Yes
`decision`	Yes	The operation that ran, one of approve, reject, cancel, refine, re_prepare or set_stage.
`attempted`	Yes
`setupStep`	No	Present while account setup is open: the first setup step.
`succeeded`	Yes
`notConfirmed`	Yes	True when the user declined the confirmation prompt and nothing was sent.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 8, 2026

changedOutput schema / properties / decision / description

Previous value: -"The operation that ran: approve, reject, cancel, refine, re_prepare or set_stage."New value: +"The operation that ran, one of approve, reject, cancel, refine, re_prepare or set_stage."

changedOutput schema / properties / results / items / properties / status / description

Previous value: -"Our own record after the action. Never proof the employer received it."New value: +"Our own record after the action, which is not proof the employer received it."

changedOutput schema / properties / setupStep / description

Previous value: -"Set while account setup is open: the step to take first."New value: +"Present while account setup is open: the first setup step."

Changed2 schema fields changedNov 8, 2026

removedOutput schema / properties / confirmToken

Removed value: -{
-  "description": "Approve of one email application only: nothing was sent yet. Show the user the exact email, then pass this as confirm_token with the same application id once they say yes. Works once, for 10 minutes, and only while the email is unchanged.",
-  "type": [
-    "string",
-    "null"
-  ]
-}

changedOutput schema / required

Previous value: -[
-  "decision",
-  "results",
-  "succeeded",
-  "attempted",
-  "notConfirmed",
-  "confirmToken"
-]New value: +[
+  "decision",
+  "results",
+  "succeeded",
+  "attempted",
+  "notConfirmed"
+]

Changed3 schema fields changedNov 8, 2026

changedInput schema / properties / steps / description

Previous value: -"The preparation steps to run again. Omit to run every step that is out of date."New value: +"The preparation steps to run again. Left out, every step that is out of date runs."

addedOutput schema / properties / confirmToken

Added value: +{
+  "description": "Approve of one email application only: nothing was sent yet. Show the user the exact email, then pass this as confirm_token with the same application id once they say yes. Works once, for 10 minutes, and only while the email is unchanged.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / required

Previous value: -[
-  "decision",
-  "results",
-  "succeeded",
-  "attempted",
-  "notConfirmed"
-]New value: +[
+  "decision",
+  "results",
+  "succeeded",
+  "attempted",
+  "notConfirmed",
+  "confirmToken"
+]

Changed1 schema field changedNov 6, 2026

addedOutput schema / properties / setupStep

Added value: +{
+  "description": "Set while account setup is open: the step to take first.",
+  "type": "string"
+}

AddedOct 25, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true and non-idempotent, so the safety profile is covered. The description adds two things annotations cannot: it consumes AI credits and it does not send anything. What is missing is whether previously generated documents are overwritten or replaced and whether that costs credits per application or per step.

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 short sentences, front-loaded with the core action, then the non-submission caveat, then the cost warning. Zero filler; only slight weakness is that the credit/cost note could have been tied to whether steps affect cost.

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?

An output schema exists and parameters are fully described, so the description only needs to carry intent, side effects, and cost. It covers regeneration semantics, the no-send guarantee, and credit usage; a note on overwrite behavior of existing documents would close the remaining gap for a destructive tool.

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%, with both parameters fully documented, including the enum of steps and the 1–25 id limit plus the pointer to getmattered_get_applications. The description adds no parameter meaning beyond the schema, so the baseline of 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?

States a specific verb and resource: rebuilds the documents and form answers of applications. The word 'again' conveys regeneration, distinguishing it from one-shot generators like getmattered_generate_cover_letter, but it never names a sibling such as getmattered_refine_application_documents, so the boundary is left for the agent to infer.

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?

'Nothing is sent' implies this is a preparation-only refresh rather than submission, which weakly signals when to use it. There is no explicit when-to-use/when-not guidance and no mention of the closest alternative (refine_application_documents) or of how it relates to an apply/approve workflow, so usage is only implied.

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

All GetMattered 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.