Forecall Failure KB

Look up known failures

kb_lookup

Read-onlyIdempotent

Check for known failures and workarounds BEFORE or AFTER calling a third-party tool. Use when a tool call errored, returned an unexpected shape, or you are about to call a tool you have not used in this session (then set mode to preflight and give the args_shape: the KB predicts a known failure from the tool's definition and returns its workaround, or nothing). Before using a server you have not used, set mode to server and leave out the tool to list its known failures. Returns the records the tool's vendor answered first, with its official_answer, then verified workarounds; unverified ones are marked. Each call takes one unit of the organization's monthly limit, returns at most max_results records, and says in units_left how many units remain. Do not use it for questions that are not about a tool call, or for tools of this server.

Input Schema

Name	Required	Description	Default
`mode`	No	lookup: find records for an error_text (default). preflight: before calling the tool, give its args_shape and your env; the KB predicts a known failure and returns its workaround, or nothing. server: leave out the tool to list the server's known failures across its tools, verified first.	lookup
`tool`	No	The tool's name as in tools/list. Required, except in the server mode.
`model`	No	The model driving the agent.
`client`	No	The client, e.g. claude-code.
`server`	Yes	The MCP server the tool belongs to: its name, or the npm package npx runs.
`args_shape`	No	The call's arguments as keys and types only, never their values.
`error_text`	No	The error message or the unexpected result, as the tool returned it.
`max_results`	No	How many records to return, from 1 to 20 (default 5).
`server_version`	No	The server's version, when known, e.g. 1.2.0: records of that version are matched.

Output Schema

Name	Required	Description
`records`	Yes
`lookup_id`	Yes
`units_left`	Yes	What the organization has left for lookups after this one.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 14, 2026

addedOutput schema / properties / records / items / properties / official_answer

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "by": {
+          "description": "The npm package whose owner answered.",
+          "type": "string"
+        },
+        "lang": {
+          "description": "The language it is written in: en or ja.",
+          "type": "string"
+        },
+        "text": {
+          "description": "The answer, in Markdown.",
+          "type": "string"
+        },
+        "updated_at": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "text",
+        "lang",
+        "by",
+        "updated_at"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "The answer of the tool's vendor, who proved to Forecall that it owns the package; null when it has not answered."
+}

changedOutput schema / properties / records / items / required

Previous value: -[
-  "id",
-  "tool",
-  "state",
-  "error_class",
-  "error_signature",
-  "workaround",
-  "reproduced_count",
-  "verified_at",
-  "url"
-]New value: +[
+  "id",
+  "tool",
+  "state",
+  "error_class",
+  "error_signature",
+  "workaround",
+  "reproduced_count",
+  "verified_at",
+  "url",
+  "official_answer"
+]

Changed8 schema fields changedOct 8, 2026

changedInput schema / properties / mode / description

Previous value: -"lookup: find records for an error_text (default). preflight: before calling the tool, give its args_shape and your env; the KB predicts a known failure and returns its workaround, or nothing."New value: +"lookup: find records for an error_text (default). preflight: before calling the tool, give its args_shape and your env; the KB predicts a known failure and returns its workaround, or nothing. server: leave out the tool to list the server's known failures across its tools, verified first."

changedInput schema / properties / mode / enum

Previous value: -[
-  "lookup",
-  "preflight"
-]New value: +[
+  "lookup",
+  "preflight",
+  "server"
+]

changedInput schema / properties / tool / description

Previous value: -"The tool's name as in tools/list."New value: +"The tool's name as in tools/list. Required, except in the server mode."

changedInput schema / required

Previous value: -[
-  "server",
-  "tool"
-]New value: +[
+  "server"
+]

addedOutput schema / properties / records / items / properties / tool
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / properties / records / items / required

Previous value: -[
-  "id",
-  "state",
-  "error_class",
-  "error_signature",
-  "workaround",
-  "reproduced_count",
-  "verified_at",
-  "url"
-]New value: +[
+  "id",
+  "tool",
+  "state",
+  "error_class",
+  "error_signature",
+  "workaround",
+  "reproduced_count",
+  "verified_at",
+  "url"
+]

addedOutput schema / properties / units_left

Added value: +{
+  "additionalProperties": false,
+  "description": "What the organization has left for lookups after this one.",
+  "properties": {
+    "credits": {
+      "description": "The organization's credits, used after them.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "resets_at": {
+      "description": "When the month's included units start again (UTC).",
+      "type": "string"
+    },
+    "this_month": {
+      "description": "The units the plan still includes this month.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    }
+  },
+  "required": [
+    "this_month",
+    "credits",
+    "resets_at"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "records",
-  "lookup_id"
-]New value: +[
+  "records",
+  "lookup_id",
+  "units_left"
+]

First observedOct 7, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations only declare read-only/idempotent/local; the description adds material behavioral context: each call consumes one unit of a monthly limit, units_left is reported, at most max_results records return, and results are ordered vendor answer first, then verified workarounds, with unverified ones marked. This is exactly the cost/return-shape disclosure annotations cannot carry.

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?

Purpose is front-loaded in the first sentence and the exclusion is saved for the end. It is one dense paragraph with long clauses, and the mode explanations partially duplicate the schema, but nearly every sentence carries operational 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?

Despite nine parameters and an output schema, the description covers everything an agent needs: when to invoke each mode, the cost per call, and the result ordering. Return values are also summarized, which is a bonus since an output schema exists.

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 the schema already documents every parameter including the mode enum. The description restates the mode semantics (preflight needs args_shape; server omits tool) but adds little beyond what the schema already says, so the baseline 3 applies.

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 ('Check for known failures and workarounds') and frames it precisely as a pre/post third-party tool call helper. It doesn't explicitly name the write-side siblings (kb_confirm, kb_dispute, kb_report), so the read-vs-report distinction is only implicit.

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?

Gives explicit triggering conditions ('a tool call errored, returned an unexpected shape, or you are about to call a tool you have not used') and explicit exclusions ('Do not use it for questions that are not about a tool call, or for tools of this server'). It even routes the agent to the correct mode for each scenario.

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

All Forecall Failure KB tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?