Jet Tracker

Replace watched registrations

jt_watch_set

DestructiveIdempotent

Replace the whole watch list of this account (idempotent: sending the same list twice changes nothing). Watched aircraft feed the account webhook with registry.changed plus business events: airworthiness.cva_expiring (30 and 7 days), airworthiness.cva_expired and flight.ground_stay. Invalid registrations are returned in invalid[] and the rest is saved. Max 500. Requires an account key (Enterprise).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`registrations`	Yes	Full list of Brazilian registrations to watch.

Output Schema

TableJSON Schema

Name	Required	Description
`code`	No	Machine-readable error code (INTERNAL, TIMEOUT, INVALID_ARGUMENT, NOT_FOUND, TOOL_FAILED, ACCOUNT_KEY_REQUIRED).
`_meta`	No
`error`	No
`found`	No
`gated`	No
`requestId`	No
`retryable`	No
`quota_exceeded`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedSep 16, 2026

addedOutput schema / properties / _meta / properties / asOf / description
```
Added value: +"Alias of sourceUpdatedAt (kept for compatibility)."
```

addedOutput schema / properties / _meta / properties / generatedAt

Added value: +{
+  "description": "When this response was produced (ISO 8601).",
+  "type": "string"
+}

addedOutput schema / properties / _meta / properties / observedAt

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Last event actually observed in the data returned (last flight, last arrival, last listing sighting)."
+}

addedOutput schema / properties / _meta / properties / sourceUpdatedAt

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Last sync of the underlying source (RAB snapshot, registry import, listing scan). Never in the future."
+}

addedOutput schema / properties / _meta / properties / validUntil

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Expiry of the fact returned, when it has one (CVA validity, period end)."
+}

addedOutput schema / properties / code

Added value: +{
+  "description": "Machine-readable error code (INTERNAL, TIMEOUT, INVALID_ARGUMENT, NOT_FOUND, TOOL_FAILED, ACCOUNT_KEY_REQUIRED).",
+  "type": "string"
+}

addedOutput schema / properties / requestId
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / retryable
```
Added value: +{
+  "type": "boolean"
+}
```

First observedSep 11, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Adds substantial behavior beyond annotations: idempotency (sending the same list twice changes nothing), the exact webhook event types and timing (registry.changed, cva_expiring at 30/7 days, etc.), invalid[] handling, max 500, and Enterprise account-key requirement. Annotations already indicate destructive/idempotent, but description enriches with concrete side effects and constraints. No contradiction with annotations.

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?

Four short sentences, action and idempotency first, followed by event details, invalid handling, and requirements. No filler; each sentence adds operational information. The event list is detailed but relevant for an agent deciding whether this watch set serves its use case.

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 write/destructive tool with one parameter, the description covers what is replaced, idempotency, side effects (webhook events), partial-failure behavior (invalid[]), size limit, and auth requirement. Output schema exists, so return format needs no further explanation. Nothing essential is missing.

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 already documents the registrations array fully (100% coverage), including Brazilian registrations and max 500. Description adds that invalid registrations are returned in invalid[] and the rest are saved, which clarifies processing behavior. This is helpful but not necessary to understand the parameter type/constraints, so baseline 3 is appropriate.

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 ('Replace'), the exact resource ('the whole watch list of this account'), and distinguishes itself from siblings like watch_add/watch_remove by emphasizing whole-list replacement. The title reinforces the resource. No ambiguity about what operation it performs.

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?

Clear context: use when you need to replace the entire watch list for an account, not incremental additions/removals. It does not explicitly name alternatives (watch_add/watch_remove), but 'whole' and the sibling list make the intended use evident. No explicit exclusions, so not a 5.

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

All Jet Tracker 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?