Update a knowledge article (requires WRITE_ENABLED=true)
Update a knowledge article (requires WRITE_ENABLED=true)
| Name | Required | Description | Default |
|---|---|---|---|
| fields | Yes | Key-value pairs to update (e.g., {"text": "...updated content..."}) | |
| sys_id | Yes | System ID of the article |
Changes observed during successful MCP inspections.
v1.15.1Input schema / properties / fields / additionalPropertiesAdded value: +falseInput schema / properties / fields / propertiesAdded value: +{
+ "category": {},
+ "kb_knowledge_base": {},
+ "short_description": {},
+ "text": {}
+}v1.0.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already disclose readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=true. The description adds the WRITE_ENABLED prerequisite, which is genuine extra context beyond the annotations, but it says nothing about partial-update semantics, what happens to omitted fields, or what the response contains.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no filler; the precondition is placed immediately after the action. It is efficient, though so terse that it leans toward under-specification rather than true completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with a nested fields object and no output schema, the description covers the essential precondition but omits update semantics — whether the update is a partial merge, whether the article must already exist, and whether it must be in draft state. An agent could call it correctly but not confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and each of the two parameters (sys_id, fields) is documented in the schema, including the nested fields object. The description adds no meaning about the fields map or whether unspecified properties are preserved, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (update) and resource (knowledge article) with the clear implication of modifying an existing article by sys_id. Sibling tools create_knowledge_article, get_knowledge_article, publish_knowledge_article and retire_knowledge_article are distinguishable by verb alone, though the description never names them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The parenthetical '(requires WRITE_ENABLED=true)' is a real usage gate, so the agent knows an environment precondition. But there is no guidance on when to use this versus publish_knowledge_article or retire_knowledge_article, which are the closest ambiguous siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.