KnowledgeRail

by Deviank88

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

knowledge_code

Destructive

Index and query code symbols, definitions, callers, and snippets, with fallback for unresolved references.

Instructions

Code index, symbols, callers, fallback.

Input Schema

TableJSON Schema

Name	Required	Description
`path`	No
`kinds`	No
`query`	No
`action`	Yes	rebuild=recreate;search=find snippets;symbol=definition;references=find callers;read=URI;record_fallback=raw lookup.
`symbol`	No
`max_chars`	No
`symbol_id`	No
`request_id`	No
`max_results`	No
`resource_uri`	No
`path_prefixes`	No
`fallback_reason`	No	no_match\|ambiguous\|unresolved_import\|unsupported_extension;else other
`recovered_evidence`	No
`fallback_result_count`	No
`fallback_result_paths`	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.

Changed1 schema field changedv2.9.1Sep 24, 2026

changedInput schema / properties / action / description

Previous value: -"rebuild=recreate;search=find;symbol=definition;references=callers;read=URI;record_fallback=raw lookup."New value: +"rebuild=recreate;search=find snippets;symbol=definition;references=find callers;read=URI;record_fallback=raw lookup."

Changed7 schema fields changedv2.9.0Sep 22, 2026

changedInput schema / properties / action / description

Previous value: -"status=index;rebuild=recreate;update=refresh;remove=drop;search=find;symbol=definition;references=callers of symbol;read=URI;record_fallback=raw lookup."New value: +"rebuild=recreate;search=find;symbol=definition;references=callers;read=URI;record_fallback=raw lookup."

addedInput schema / properties / fallback_reason / description

Added value: +"no_match|ambiguous|unresolved_import|unsupported_extension;else other"

changedInput schema / properties / kinds / items / enum

Previous value: -[
-  "module",
-  "class",
-  "function",
-  "method",
-  "route",
-  "test",
-  "comment"
-]New value: +[
+  "module",
+  "class",
+  "function",
+  "method",
+  "constant",
+  "route",
+  "test",
+  "comment"
+]

changedInput schema / properties / kinds / maxItems
```
Previous value: -7New value: +8
```

addedInput schema / properties / request_id

Added value: +{
+  "maxLength": 36,
+  "type": "string"
+}

addedInput schema / properties / resource_uri / format
```
Added value: +"starts_with"
```
removedOutput schema / additionalProperties
```
Removed value: -true
```

First observedv2.7.0Sep 1, 2026

TDQS

D1.6/5.0

Behavior2/5

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

Annotations already carry the safety profile (destructiveHint=true, readOnlyHint=false), so the description needn't repeat it, but it adds no behavioral context: no mention that rebuild/update/remove mutate or destroy index state, no explanation of what 'fallback' entails, and no rate/authorization caveats. The bare word 'fallback' hints at behavior without disclosing it. No contradiction with 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 four words the description is short, but this is under-specification, not conciseness. There is no front-loaded purpose statement or sentence structure, and 'fallback' dangles without explanation. The brevity is achieved by discarding all substance rather than by trimming excess.

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?

For a tool with 9 action modes, 15 parameters, index-mutation operations, and fallback-recording semantics, a four-word fragment is grossly inadequate. Even with an output schema available, the description fails to explain action selection, the difference between search/symbol/references/read, the required code://repo/ resource_uri format, or the destructive lifecycle — all of which an agent needs to invoke it correctly.

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?

Schema description coverage is only 13% (solely the action enum labels), so the description must compensate — and it doesn't. None of the 15 parameters (path, kinds, query, symbol, resource_uri, recovered_evidence, etc.) are explained in the description. The four-word fragment adds no parameter meaning beyond what the schema already structurally shows.

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, "Code index, symbols, callers, fallback," is a noun-phrase fragment with no verb stating what the tool does. 'Code index' loosely restates the tool name, and 'symbols'/'callers'/'fallback' hint at the domain but never state an action. An agent must open the action enum to learn the tool can rebuild, update, remove, search, read, and record fallback data.

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

Usage Guidelines1/5

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

No guidance is given for when to use this tool over siblings like knowledge_document, knowledge_files, or knowledge_admin. There is no 'use when' condition, no exclusions, and no mention of alternatives. The keyword fragment leaves tool selection entirely to inference from the schema.

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

Deploy Server