KnowledgeRail

by Deviank88

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

knowledge_ingest

Destructive

Ingest source documentation and code to extract claims, track coverage, and identify evidence gaps for AI agents.

Instructions

Source ingestion, claims, coverage, recovery.

Input Schema

TableJSON Schema

Name	Required	Description
`action`	Yes	start=begin;next=read segment;apply_claims=integrate;record_segment=classify;source_status=coverage;evidence_status=debt;report=drafts.
`claims`	No	target:page_path,page_title,page_type,code_resource_uri. Stakeholders:entity_key,role,organization,email_domain,affiliation.
`reason`	No
`claim_ids`	No
`max_chars`	No
`page_refs`	No
`segment_id`	No
`evidence_refs`	No
`segment_status`	No
`recovery_events`	No
`recovery_reason`	No
`report_filename`	No
`include_resolved`	No
`recovery_event_id`	No
`segment_max_chars`	No
`recovery_page_refs`	No
`normalized_filename`	No
`recovery_resolution`	No
`total_evidence_used`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`state`	Yes
`guidance`	No
`nextAction`	Yes
`resultText`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv2.9.0Sep 22, 2026

changedInput schema / properties / action / description

Previous value: -"start=begin;next=segment;apply_claims=integrate claims;record_segment=classify;source_status=coverage;evidence_status=debt;finalize=close;report=drafts;record_recovery=track;resolve_recovery=resolve."New value: +"start=begin;next=read segment;apply_claims=integrate;record_segment=classify;source_status=coverage;evidence_status=debt;report=drafts."

changedInput schema / properties / claims / description

Previous value: -"Stakeholder target: entity_key,page_path,page_title,page_type,role,organization,email_domain,affiliation."New value: +"target:page_path,page_title,page_type,code_resource_uri. Stakeholders:entity_key,role,organization,email_domain,affiliation."

removedOutput schema / additionalProperties
```
Removed value: -true
```

Changed2 schema fields changedv2.7.2Sep 2, 2026

changedInput schema / properties / claims / description

Previous value: -"Claims; target/relations optional."New value: +"Stakeholder target: entity_key,page_path,page_title,page_type,role,organization,email_domain,affiliation."

removedInput schema / properties / recovery_events / description
```
Removed value: -"Recovery events; pages optional."
```

First observedv2.7.0Sep 1, 2026

TDQS

D1.8/5.0

Behavior2/5

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

Annotations indicate destructiveHint=true and readOnlyHint=false, so the tool is known to be mutating, but the description adds no behavioral context. It does not disclose side effects, what becomes destroyed, phasing behavior, or state changes across the ingest lifecycle. The description neither contradicts nor enriches the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

At six words, the description is brief, but brevity here is under-specification rather than efficient conciseness. There is no front-loaded actionable verb, and the noun list could apply to many tools. It does not earn its place because it communicates almost nothing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex, destructive, multi-action tool with 19 parameters and an output schema, yet the description gives no protocol-level guidance. An agent cannot determine how to start ingestion, advance segments, apply claims, or handle recovery from either the description or the sparse schema hints. The definition is far from complete for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at only 11% and 19 parameters, the description needed to compensate, but it names no parameters at all. It does not explain claims, segment_id, recovery_events, page_refs, or any other parameter's role. The action enum in the schema carries the only real parameter guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Source ingestion, claims, coverage, recovery.' is a set of nouns, not a statement of behavior. It does not say what the tool does with a clear verb, and it does not distinguish knowledge_ingest from sibling tools like knowledge_document or knowledge_admin. The purpose is vaguely implied rather than specified.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description offers no guidance about when to use this tool versus knowledge_files, knowledge_context, knowledge_page, or other siblings. It also does not explain which of the ten possible 'action' values should be chosen in which situation. No exclusions or alternatives are mentioned.

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

Deploy Server