Skip to main content
Glama

Hyreflow

by ai.hyreflow
OverviewDiscussionsAdmin

hyreflow_enrich_run

Destructive

Run ordered enrichment steps over a list of rows, each row independently (the CSV-style, per-column executor). Returns a summary with a cost estimate, not raw rows. Rows come from rows, or from a stored dataset via input (its ds_ id), in which case the whole dataset is enriched into a NEW dataset (_meta.dataset_id). Enrichment adds data only; it does not screen or filter rows. The call waits about 20s: a longer run returns _meta.status: "running" and a run_id, and a call with only run_id returns its progress at no charge. A row still processing at the provider reads still_enriching, which ends that row's chain, and carries a job_id, a resume {tool, method, id_arg} and, when fetchable, a job {provider, job_id} handle. A still_enriching row is NOT a miss: its email is still being fetched and usually arrives within 1-2 minutes. _meta.pending counts such rows and _meta.instruction says how to re-check them (free) every _meta.poll_after_s seconds until _meta.pending is 0. Resending an identical run within 15 minutes returns the first one, charged 0. The quote's expected_credits is the typical cost; total_max_credits the worst case.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rowsNo
inputNoA ds_ dataset id to enrich instead of `rows`.
stepsNoOrdered per-column steps: direct specs, wrapped with specs, or waterfall groups.
run_idNoThe `run_id` of an earlier call that returned running. Sent alone, it returns that run's progress (with user_prompt). Free.
dry_runNo
user_promptYesThe user's request that drove this call, verbatim as they phrased it. Recorded with the run so its trace reads as the ask followed by the calls it drove.
confirm_tokenNoThe `confirm_token` returned by a previous identical call that came back `confirmation_required`. Required to run a call above the workspace's confirmation threshold.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / steps / items / oneOf
      Previous value: -[
-  {
-    "properties": {
-      "alias": {
-        "type": "string"
-      },
-      "extract_js": {
-        "type": "string"
-      },
-      "method": {
-        "type": "string"
-      },
-      "payload": {
-        "type": "object"
-      },
-      "tool": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "alias",
-      "tool"
-    ],
-    "type": "object"
-  },
-  {
-    "properties": {
-      "kind": {
-        "const": "with"
-      },
-      "spec": {
-        "properties": {
-          "alias": {
-            "type": "string"
-          },
-          "extract_js": {
-            "type": "string"
-          },
-          "method": {
-            "type": "string"
-          },
-          "payload": {
-            "type": "object"
-          },
-          "tool": {
-            "type": "string"
-          }
-        },
-        "required": [
-          "alias",
-          "tool"
-        ],
-        "type": "object"
-      }
-    },
-    "required": [
-      "kind",
-      "spec"
-    ],
-    "type": "object"
-  },
-  {
-    "properties": {
-      "kind": {
-        "const": "waterfall"
-      },
-      "name": {
-        "type": "string"
-      },
-      "specs": {
-        "items": {
-          "properties": {
-            "alias": {
-              "type": "string"
-            },
-            "extract_js": {
-              "type": "string"
-            },
-            "method": {
-              "type": "string"
-            },
-            "payload": {
-              "type": "object"
-            },
-            "tool": {
-              "type": "string"
-            }
-          },
-          "required": [
-            "alias",
-            "tool"
-          ],
-          "type": "object"
-        },
-        "minItems": 1,
-        "type": "array"
-      }
-    },
-    "required": [
-      "kind",
-      "name",
-      "specs"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "properties": {
+      "alias": {
+        "type": "string"
+      },
+      "extract_js": {
+        "type": "string"
+      },
+      "method": {
+        "type": "string"
+      },
+      "payload": {
+        "description": "Request body for a provider tool, with {{column}} templates filled per row, e.g. {\"linkedin_url\": \"{{linkedin_url}}\"}. Required for a provider tool. A waterfall capability (linkedin_profile, personal_email, …) may omit it and runs on the row itself.",
+        "type": "object"
+      },
+      "tool": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "alias",
+      "tool"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "kind": {
+        "const": "with"
+      },
+      "spec": {
+        "properties": {
+          "alias": {
+            "type": "string"
+          },
+          "extract_js": {
+            "type": "string"
+          },
+          "method": {
+            "type": "string"
+          },
+          "payload": {
+            "description": "Request body for a provider tool, with {{column}} templates filled per row, e.g. {\"linkedin_url\": \"{{linkedin_url}}\"}. Required for a provider tool. A waterfall capability (linkedin_profile, personal_email, …) may omit it and runs on the row itself.",
+            "type": "object"
+          },
+          "tool": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "alias",
+          "tool"
+        ],
+        "type": "object"
+      }
+    },
+    "required": [
+      "kind",
+      "spec"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "kind": {
+        "const": "waterfall"
+      },
+      "name": {
+        "type": "string"
+      },
+      "specs": {
+        "items": {
+          "properties": {
+            "alias": {
+              "type": "string"
+            },
+            "extract_js": {
+              "type": "string"
+            },
+            "method": {
+              "type": "string"
+            },
+            "payload": {
+              "description": "Request body for a provider tool, with {{column}} templates filled per row, e.g. {\"linkedin_url\": \"{{linkedin_url}}\"}. Required for a provider tool. A waterfall capability (linkedin_profile, personal_email, …) may omit it and runs on the row itself.",
+              "type": "object"
+            },
+            "tool": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "alias",
+            "tool"
+          ],
+          "type": "object"
+        },
+        "minItems": 1,
+        "type": "array"
+      }
+    },
+    "required": [
+      "kind",
+      "name",
+      "specs"
+    ],
+    "type": "object"
+  }
+]
  2. Changed3 schema fields changed
    • changedInput schema / properties / confirm_token / description
      Previous value: -"Echo of the `confirm_token` a previous identical call returned with `confirmation_required`, after the user approved the quoted cost."New value: +"The `confirm_token` returned by a previous identical call that came back `confirmation_required`. Required to run a call above the workspace's confirmation threshold."
    • changedInput schema / properties / run_id / description
      Previous value: -"Poll a run an earlier call handed back running — send only this (and user_prompt). Free."New value: +"The `run_id` of an earlier call that returned running. Sent alone, it returns that run's progress (with user_prompt). Free."
    • changedInput schema / properties / user_prompt / description
      Previous value: -"The user's request that drove this call, verbatim as they phrased it. Never a paraphrase, and never ask the user for it."New value: +"The user's request that drove this call, verbatim as they phrased it. Recorded with the run so its trace reads as the ask followed by the calls it drove."
  3. Changed2 schema fields changed
    • addedInput schema / properties / run_id
      Added value: +{
+  "description": "Poll a run an earlier call handed back running — send only this (and user_prompt). Free.",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "steps",
-  "user_prompt"
-]New value: +[
+  "user_prompt"
+]
  4. Changed2 schema fields changed
    • addedInput schema / properties / input
      Added value: +{
+  "description": "A ds_ dataset id to enrich instead of `rows`.",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "rows",
-  "steps",
-  "user_prompt"
-]New value: +[
+  "steps",
+  "user_prompt"
+]
  5. Changed1 schema field changed
    • addedInput schema / properties / confirm_token
      Added value: +{
+  "description": "Echo of the `confirm_token` a previous identical call returned with `confirmation_required`, after the user approved the quoted cost.",
+  "type": "string"
+}
  6. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations it discloses substantial behavior: the ~20s wait, the running/run_id return shape, the free run_id progress re-check, the still_enriching semantics and why it is not a miss, pending/poll_after_s polling, the 15-minute idempotency dedup charged at 0, and the expected_credits vs total_max_credits cost model. This is exactly the behavioral depth an agent needs for a long-running, billing-sensitive call.

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 purpose, output shape, and data source before the operational details, and each sentence carries real information. It is a dense single block with no formatting, which slightly taxes readability, but little could be cut without losing behavioral value.

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 complex, open-world, credit-spending tool with no output schema, the description covers sourcing, mutation scope, timing/async behavior, partial-result semantics, polling, idempotency, and cost. Nothing essential to calling 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?

With 71% schema coverage the baseline is 3, and the description adds genuine meaning beyond the schema: `input` (ds_ id) enriches the whole dataset into a NEW dataset, and a run_id-only call yields free progress. It does not elaborate the steps spec structure (direct/with/waterfall), which remains largely schema-only.

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?

Opens with a specific verb and resource ('Run ordered enrichment steps over a list of rows') and self-differentiates as 'the CSV-style, per-column executor', which separates it from sibling job/workflow tools. It also immediately clarifies the output shape ('Returns a summary with a cost estimate, not raw rows'). An agent can identify this tool without opening a schema.

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?

Gives clear operational context: rows come from `rows` or a stored dataset via `input`, and a run_id-only call returns progress for free. However, it never names an alternative (e.g. hyreflow_enrich_job, hyreflow_workflow_run) or states when-not-to-use, so the selection guidance is implied rather than explicit.

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

All Hyreflow toolsInspect
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