Previous value: -"Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""New value: +"Brief purpose of this tool call within the requested task, used for analytics and user-intent tracking."

Previous value: -"optional nudge. 'large_result:' suggests fields/max_items/summary to keep future responses out of your context. 'paging_unavailable:' means this result came from a source that cannot return a nextCursor, so it may be INCOMPLETE and you cannot page further - re-run with requireFields [\"nextCursor\"] (may cost more per request) if you need the full list. 'malformed_query:' means X read your search query differently than it looks (adjacent bare words are ANDed and OR binds tighter, so a multi-word alternative is not a phrase); this result is what X returned for it, and the hint carries the corrected query to send next time. 'date_adjusted:' means a date you sent was outside the range the platform accepts, so the run used the nearest accepted date the hint names"New value: +"optional result caveat. 'large_result:' identifies a large response; fields/max_items/summary reduce response size without changing cost. 'paging_unavailable:' means the source cannot return a nextCursor, so the result may be incomplete and cannot be paged further; requireFields [\"nextCursor\"] restricts execution to sources that support pagination and may cost more per request. 'malformed_query:' means X interpreted adjacent bare words as ANDed and OR as having higher precedence, so a multi-word alternative is not a phrase; the result reflects that interpretation, and the hint includes a corrected query. 'date_adjusted:' means an input date was outside the platform's accepted range, so execution used the nearest accepted date named in the hint"

Previous value: -"machine-actionable resume instruction present while durable work is pending"New value: +"stored-request retrieval coordinates and polling interval present while durable work is pending"

Previous value: -"request_id argument for the next tool call"New value: +"durable request identifier for stored-request retrieval"

Previous value: -"MCP tool to call next"New value: +"MCP tool name for stored-request retrieval"

Previous value: -"durable request identifier; pass it to get_request to resume without repeating the paid POST"New value: +"durable request identifier for stored status and result retrieval without repeating the paid provider dispatch"

Previous value: -"opaque handle to the full result, cached ~15 min; pass it to read_result to dig deeper for free (no re-run, no charge). Absent when the result was too large to cache"New value: +"opaque handle to the full result, cached ~15 min; identifies the paid result available for free reshaping without another execution or charge. Absent when the result was too large to cache"

Previous value: -"the source that served this run: pass its id back in 'source' to prefer it again, or in 'ignoreSources' to avoid it. Absent when no source identity applies"New value: +"the source that served this request; its id is accepted by 'source' for preference or 'ignoreSources' for exclusion. Absent when no source identity applies"

Previous value: -"optional nudge. 'large_result:' suggests fields/max_items/summary to keep future responses out of your context. 'paging_unavailable:' means this result came from a source that cannot return a nextCursor, so it may be INCOMPLETE and you cannot page further - re-run with requireFields [\"nextCursor\"] (may cost more per request) if you need the full list. 'malformed_query:' means X read your search query differently than it looks (adjacent bare words are ANDed and OR binds tighter, so a multi-word alternative is not a phrase); this result is what X returned for it, and the hint carries the corrected query to send next time"New value: +"optional nudge. 'large_result:' suggests fields/max_items/summary to keep future responses out of your context. 'paging_unavailable:' means this result came from a source that cannot return a nextCursor, so it may be INCOMPLETE and you cannot page further - re-run with requireFields [\"nextCursor\"] (may cost more per request) if you need the full list. 'malformed_query:' means X read your search query differently than it looks (adjacent bare words are ANDed and OR binds tighter, so a multi-word alternative is not a phrase); this result is what X returned for it, and the hint carries the corrected query to send next time. 'date_adjusted:' means a date you sent was outside the range the platform accepts, so the run used the nearest accepted date the hint names"

Previous value: -"optional nudge. 'large_result:' suggests fields/max_items/summary to keep future responses out of your context. 'paging_unavailable:' means this result came from a source that cannot return a nextCursor, so it may be INCOMPLETE and you cannot page further - re-run with requireFields [\"nextCursor\"] (may cost more per request) if you need the full list"New value: +"optional nudge. 'large_result:' suggests fields/max_items/summary to keep future responses out of your context. 'paging_unavailable:' means this result came from a source that cannot return a nextCursor, so it may be INCOMPLETE and you cannot page further - re-run with requireFields [\"nextCursor\"] (may cost more per request) if you need the full list. 'malformed_query:' means X read your search query differently than it looks (adjacent bare words are ANDed and OR binds tighter, so a multi-word alternative is not a phrase); this result is what X returned for it, and the hint carries the corrected query to send next time"

Previous value: -"optional: keep only these keys on each result item (dotted paths like 'author.name' descend into nested objects). Shrinks the response without changing cost"New value: +"optional: keep only these keys on each result item - each row of the result list, or the data object itself for an API that returns one record (dotted paths like 'author.name' descend into nested objects). Shrinks the response without changing cost"

Previous value: -"optional: cap the number of result items returned; a _truncated note reports how many were withheld. Does not change cost"New value: +"optional: cap the number of result items returned; a _truncated note reports how many were withheld. An API that returns one record is not trimmed. Does not change cost"

Previous value: -"number of result rows returned. For per-result SKUs the per-item cost is charged against this; for input-priced SKUs (perItemUnit != result) the charge is per submitted input, independent of this count"New value: +"number of result rows returned; an API that returns one record counts it as one row. For per-result APIs the per-item cost is charged against this; for input-priced APIs (perItemUnit != result) the charge is per submitted input, independent of this count"

Added value: +{
+  "additionalProperties": false,
+  "description": "the source that served this run: pass its id back in 'source' to prefer it again, or in 'ignoreSources' to avoid it. Absent when no source identity applies",
+  "properties": {
+    "artworkKey": {
+      "type": "string"
+    },
+    "id": {
+      "type": "string"
+    },
+    "kind": {
+      "type": "string"
+    },
+    "name": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "id",
+    "name",
+    "kind",
+    "artworkKey"
+  ],
+  "type": [
+    "null",
+    "object"
+  ]
+}

Previous value: -"optional nudge. 'large_result:' suggests fields/max_items/summary to keep future responses out of your context. 'paging_unavailable:' means this result came from a source that cannot return a nextCursor, so it may be INCOMPLETE and you cannot page further - re-run with requireCursor true (may cost more per request) if you need the full list"New value: +"optional nudge. 'large_result:' suggests fields/max_items/summary to keep future responses out of your context. 'paging_unavailable:' means this result came from a source that cannot return a nextCursor, so it may be INCOMPLETE and you cannot page further - re-run with requireFields [\"nextCursor\"] (may cost more per request) if you need the full list"

Removed value: -false

Added value: +{
+  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
+  "type": "string"
+}

Previous value: -[
-  "sku_id",
-  "input"
-]New value: +[
+  "sku_id",
+  "input",
+  "context"
+]

Added value: +{
+  "additionalProperties": false,
+  "description": "safe AnyAPI failure code when durable work failed",
+  "properties": {
+    "code": {
+      "description": "safe AnyAPI error code",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code"
+  ],
+  "type": [
+    "null",
+    "object"
+  ]
+}

Previous value: -"optional nudge, present only on large untrimmed results, suggesting fields/max_items/summary to keep future responses out of your context"New value: +"optional nudge. 'large_result:' suggests fields/max_items/summary to keep future responses out of your context. 'paging_unavailable:' means this result came from a source that cannot return a nextCursor, so it may be INCOMPLETE and you cannot page further - re-run with requireCursor true (may cost more per request) if you need the full list"

Added value: +{
+  "additionalProperties": false,
+  "description": "machine-actionable resume instruction present while durable work is pending",
+  "properties": {
+    "requestId": {
+      "description": "request_id argument for the next tool call",
+      "type": "string"
+    },
+    "retryAfterSeconds": {
+      "description": "minimum delay before polling again",
+      "type": "integer"
+    },
+    "tool": {
+      "description": "MCP tool to call next",
+      "type": "string"
+    }
+  },
+  "required": [
+    "tool",
+    "requestId",
+    "retryAfterSeconds"
+  ],
+  "type": [
+    "null",
+    "object"
+  ]
+}

Added value: +{
+  "description": "true when this response replays an identical earlier call (same API, same input) from the last few minutes instead of running again: nothing new was executed and costUsd restates the original charge, it was NOT charged a second time",
+  "type": "boolean"
+}

Added value: +{
+  "description": "durable request identifier; pass it to get_request to resume without repeating the paid POST",
+  "type": "string"
+}

Added value: +{
+  "description": "end-to-end AnyAPI service outcome when known",
+  "type": "string"
+}

Added value: +{
+  "description": "payment settlement state when known; independent of durable request status",
+  "type": "string"
+}

Added value: +{
+  "description": "durable request status: queued, running, succeeded, failed, or expired",
+  "type": "string"
+}

Previous value: -[
-  "output",
-  "provider",
-  "costUsd",
-  "items"
-]New value: +[
+  "output",
+  "provider",
+  "costUsd",
+  "items",
+  "replayed"
+]

Added value: +{
+  "description": "optional: a jq expression to reshape the result; its output replaces 'output' (multiple outputs collect into an array). Example: '.data | {title, description, md: .markdown[:3500]}'. Sandboxed 250ms/2MB budget; on failure the full result is returned with jqError. Does not change cost",
+  "type": "string"
+}

Previous value: -"optional: return only a structural outline (top-level keys and item counts) instead of the full data. Does not change cost"New value: +"optional: return only a structural outline (top-level keys, item counts, and per-field byte sizes) instead of the full data. Does not change cost"

Added value: +{
+  "description": "present only when a jq expression failed; output then holds the full unshaped result and this explains why the reshape did not apply",
+  "type": "string"
+}

Added value: +{
+  "description": "opaque handle to the full result, cached ~15 min; pass it to read_result to dig deeper for free (no re-run, no charge). Absent when the result was too large to cache",
+  "type": "string"
+}