viajante

Overview Schema Source Related Servers Discussions Admin

Verify draft answer

verify_answer

Read-onlyIdempotent

Check draft replies against recent search payloads to flag fares, dates, airport codes, and links not returned by searches, so you can re-search or drop them.

Instructions

Check a draft reply against this process's recent search payloads.

Call before sending a reply that quotes fares, stays, dates, airport codes, or links. Lists each amount, currency, IATA code, ISO date, and URL in the draft that no recorded search returned. Drop or re-search every unowned row; do not quote it as found. Sums you computed are unowned unless a payload carries them (e.g. trip_total). Local; may run during a search.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`answer`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`status`	Yes
`empty_note`	Yes
`error_code`	Yes
`observed_at`	Yes
`retry_after`	Yes
`completeness`	Yes
`empty_reason`	Yes
`observed_at_basis`	Yes
`retry_after_seconds`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv1.5.2Oct 19, 2026

removedInput schema / properties / answer / title
```
Removed value: -"Answer"
```

removedInput schema / title

Removed value: -"verify_answerArguments"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "completeness": {
+      "enum": [
+        "complete",
+        "partial",
+        "blocked"
+      ],
+      "type": "string"
+    },
+    "empty_note": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "empty_reason": {
+      "anyOf": [
+        {
+          "enum": [
+            "provider_empty",
+            "filtered_out",
+            "not_loaded"
+          ],
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "error_code": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "observed_at": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "observed_at_basis": {
+      "anyOf": [
+        {
+          "enum": [
+            "provider",
+            "fetch"
+          ],
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "retry_after": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "retry_after_seconds": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "status": {
+      "enum": [
+        "ok",
+        "no_results",
+        "rate_limited",
+        "blocked",
+        "timeout",
+        "failed"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "status",
+    "completeness",
+    "empty_reason",
+    "empty_note",
+    "error_code",
+    "retry_after",
+    "retry_after_seconds",
+    "observed_at",
+    "observed_at_basis"
+  ],
+  "type": "object"
+}

Addedv1.4.1Oct 6, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), but the description adds substantial semantics beyond them: what the tool returns (each unowned amount/currency/IATA code/ISO date/URL), the edge case that agent-computed sums count as unowned unless a payload carries them, and execution context ('Local; may run during a search'). This is rich, non-redundant behavioral context.

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?

Front-loaded purpose, then trigger, then output semantics, then the computed-sum caveat, then the execution note. Every sentence adds distinct, actionable information with no filler.

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?

Purpose, trigger, output meaning, and the key edge case are all covered, and an output schema exists so return structure needn't be restated. Nothing an agent needs in order to call it correctly 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 description coverage is 0%, so the description must carry the burden, and it does partially: 'Check a draft reply' tells the agent the single 'answer' parameter is the draft reply text. It stops short of stating format or length constraints, so it compensates but not fully.

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 description states a specific verb (check/verify) and resource (a draft reply against recorded search payloads), and it clearly distinguishes itself from the sibling search_* and lookup_* tools by being a pre-send validation gate. An agent can tell exactly what it does without opening the 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?

It gives an explicit trigger condition — 'Call before sending a reply that quotes fares, stays, dates, airport codes, or links' — and prescribes the follow-up action ('Drop or re-search every unowned row; do not quote it as found'). Nothing about when to invoke it is left to inference.

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