KnowledgeRail

Overview Schema Source Related Servers Discussions Admin

knowledge_context

Read-onlyIdempotent

Retrieve evidence-backed project context from documentation and code, with searchable pages, passages, and relation graphs, while reporting knowledge gaps.

Instructions

Evidence/gaps, pages, search, and graph.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mode`	No	task=evidence/gaps;list=pages;search=passages;graph=relations/dependencies.	task
`view`	No		subgraph
`as_of`	No	Claim validity at a UTC ISO timestamp.
`query`	No
`intent`	No		understand
`max_depth`	No
`max_nodes`	No
`objective`	No
`page_types`	No
`max_results`	No
`max_evidence`	No
`changed_paths`	No
`response_detail`	No		compact
`retrieval_profile`	No		balanced
`heuristic_token_budget`	No
`include_repository_map`	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.

Changed4 schema fields changedv2.9.0Sep 22, 2026

addedInput schema / properties / as_of

Added value: +{
+  "description": "Claim validity at a UTC ISO timestamp.",
+  "type": "string"
+}

addedInput schema / properties / include_repository_map
```
Added value: +{
+  "type": "boolean"
+}
```

changedInput schema / properties / mode / description

Previous value: -"task=evidence/gaps; list=pages; search=passages; graph=relations/dependencies."New value: +"task=evidence/gaps;list=pages;search=passages;graph=relations/dependencies."

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

First observedv2.7.0Sep 1, 2026

TDQS

C2.2/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. However, the description adds no behavioral context beyond a bare list of concepts, such as whether results are aggregated, how graph traversal behaves, or what 'evidence/gaps' means operationally. It neither contradicts the annotations nor enriches them.

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?

The description is brief, but brevity here is under-specification rather than effective conciseness. It is an unstructured comma-separated list with no front-loaded verb or explanation. For a tool with 16 parameters, this does not earn its place as a useful summary.

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?

Given the tool's complexity (16 parameters, 5 enums, 8 siblings) and the existence of an output schema, the description still leaves an agent without enough orientation to select or invoke the tool correctly. It does not explain what kind of context is returned, how modes relate to sibling tools, or what scenarios warrant using this tool. The output schema and annotations cannot compensate for this lack of usage context.

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

Parameters2/5

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

Schema description coverage is only 13%, so the description must compensate for poorly documented parameters. It does not: 'Evidence/gaps, pages, search, and graph' loosely maps to the mode enum but says nothing about query, objective, max_depth, max_nodes, retrieval_profile, or the other 13 parameters. The description adds almost no meaning beyond the schema's own mode descriptions.

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

Purpose3/5

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

The description 'Evidence/gaps, pages, search, and graph' names several sub-resources but does not state a clear action or outcome, so the tool's purpose remains vague. It does not differentiate knowledge_context from siblings such as knowledge_page or knowledge_document_context. This is more than a pure tautology but far from a specific verb+resource statement.

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?

There is no guidance on when to use this tool versus sibling tools like knowledge_page, knowledge_code, or knowledge_document_context. The mode enum in the schema hints at different behaviors, but the description itself provides no selection criteria or exclusions. An agent must infer usage from parameter names and sibling names.

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

Deploy Server