Pipeworx

Search Packs

search_packs

Read-onlyIdempotent

Search Pipeworx packs by keyword or a plain question across pack names, descriptions and tool descriptions (e.g. "weather", "translate", "Colombia procurement contracts awarded to a supplier"). Returns matching packs ranked best-first with each one's matched terms, cost, auth and reliability. Use to find which pack covers a capability before connecting to it; question filler and proper names are ignored, so the subject words are what match.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum packs to return, best match first (1-200, default 25).
`query`	Yes	Keywords or a question naming the data you want. The subject words match (country, system, dataset, topic); names of specific companies or people do not, since no pack describes them.

Output Schema

TableJSON Schema

Name	Required	Description
`hint`	No	Present only when no pack matched: how to rephrase, or use ask_pipeworx
`packs`	Yes	Matching packs
`query`	Yes	Search query used
`results`	Yes	Number of matching packs
`showing`	No	Packs returned when the match list was capped by limit
`truncated`	No	True when more packs matched than were returned

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 10, 2026

addedOutput schema / properties / packs / items / properties / next_step

Added value: +{
+  "description": "The exact next request to make for the first named tool, in the shape of the surface this call arrived on (REST /v1/tools/{name}, or MCP tools/call)",
+  "type": "string"
+}

addedOutput schema / properties / packs / items / properties / tools

Added value: +{
+  "description": "Up to 3 tools in this pack that best match the query, by the EXPOSED name — the one GET/POST /v1/tools/{name} resolves, namespaced when several packs export the same tool name. Not the pack's full list; call get_pack_tools for that.",
+  "items": {
+    "properties": {
+      "name": {
+        "description": "Exact tool name to call, e.g. fred_get_series",
+        "type": "string"
+      },
+      "summary": {
+        "description": "One line on what the tool returns",
+        "type": "string"
+      }
+    },
+    "required": [
+      "name",
+      "summary"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Changed7 schema fields changedSep 3, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "query": "weather"
-  },
-  {
-    "query": "translate"
-  }
-]New value: +[
+  {
+    "query": "weather"
+  },
+  {
+    "query": "translate"
+  },
+  {
+    "limit": 3,
+    "query": "Which public contracts has the supplier Constructora Conconcreto been awarded recently in Colombia SECOP procurement system"
+  }
+]

addedInput schema / properties / limit

Added value: +{
+  "description": "Maximum packs to return, best match first (1-200, default 25).",
+  "type": "number"
+}

changedInput schema / properties / query / description

Previous value: -"Search query"New value: +"Keywords or a question naming the data you want. The subject words match (country, system, dataset, topic); names of specific companies or people do not, since no pack describes them."

addedOutput schema / properties / hint

Added value: +{
+  "description": "Present only when no pack matched: how to rephrase, or use ask_pipeworx",
+  "type": "string"
+}

addedOutput schema / properties / packs / items / properties / matched_terms

Added value: +{
+  "description": "Query words found in this pack's text, best match first",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / showing

Added value: +{
+  "description": "Packs returned when the match list was capped by limit",
+  "type": "number"
+}

addedOutput schema / properties / truncated

Added value: +{
+  "description": "True when more packs matched than were returned",
+  "type": "boolean"
+}

Changed1 schema field changedMay 13, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "packs": {
+      "description": "Matching packs",
+      "items": {
+        "properties": {
+          "category": {
+            "description": "Pack category",
+            "type": "string"
+          },
+          "description": {
+            "description": "Pack description",
+            "type": "string"
+          },
+          "gateway_url": {
+            "description": "MCP gateway URL for the pack",
+            "type": "string"
+          },
+          "name": {
+            "description": "Pack display name",
+            "type": "string"
+          },
+          "slug": {
+            "description": "Pack identifier slug",
+            "type": "string"
+          }
+        },
+        "required": [
+          "slug",
+          "name",
+          "description",
+          "category",
+          "gateway_url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "query": {
+      "description": "Search query used",
+      "type": "string"
+    },
+    "results": {
+      "description": "Number of matching packs",
+      "type": "number"
+    }
+  },
+  "required": [
+    "query",
+    "results",
+    "packs"
+  ],
+  "type": "object"
+}

Changed1 schema field changedMay 6, 2026

addedInput schema / examples

Added value: +[
+  {
+    "query": "weather"
+  },
+  {
+    "query": "translate"
+  }
+]

First observedApr 22, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already establish read-only, idempotent, closed-world safety, so the bar is lower. The description adds real behavioral context by explaining the matching semantics (question filler and proper names ignored, subject words match) and that results carry matched terms, cost, auth and reliability.

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 sentences, front-loaded with the core action, and the inline examples do real work for a fuzzy search tool. Slightly dense but no wasted clauses.

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?

With an output schema present, return values need not be detailed, and the description still sketches what comes back. Combined with 100% schema coverage and safety annotations, an agent has everything needed to call it correctly; only sibling selection is left implicit.

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 description coverage is 100%, so both params are already documented, establishing the baseline of 3. The description reinforces the query semantics with examples but adds no detail on limit and nothing the schema does not already state.

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 ('Search Pipeworx packs') plus the exact scope searched (pack names, descriptions, tool descriptions) and gives three concrete example queries. It does not name any sibling (e.g. list_packs or discover_tools) to route the agent, so it is clear but not differentiated.

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?

'Use to find which pack covers a capability before connecting to it' gives a clear use context. No explicit when-not or named alternatives are provided, but the intended trigger is unambiguous for a discovery tool.

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

All Pipeworx tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.