Need to add context to a knowledge base session? Append a user, assistant, or tool message to keep the conversation going.
Append a message to a KB ask session
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| role | No | Defaults to user when omitted | |
| content | Yes | Plain text, OR a JSON-encoded array of content blocks ({type:"text"|"tool_use"|"tool_result", ...}) |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not add behavioral context beyond the annotations. 'Append' is consistent with readOnlyHint=false, but there is no disclosure about ordering, validation, idempotency, or what happens when the session does not exist. Annotation_contradiction is false, but no extra behavioral insight is provided.
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 sentence with no wasted words and the verb-resource pair front-loaded. It is concise and easy to parse, though it borders on under-specification rather than genuine 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 simple append operation with three parameters, the schema handles most parameter semantics, but the description omits any note about return value, error conditions, or how this relates to session lifecycle tools. It is minimally viable but leaves room for confusion around usage and expected behavior.
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 coverage is 67%, with role and content already described in the schema. The tool description at least clarifies that id refers to a 'KB ask session', which adds a small amount of meaning to the bare string property. However, the description does not explain the content block format or role semantics beyond what the schema provides.
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?
The description names a specific verb ('Append') and resource ('a KB ask session'), making it clear the tool writes a message into a knowledge-base ask session. It is not fully differentiated from siblings like invariance_kb_session_create or invariance_session_append_note, but the resource is specific enough to be understood.
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?
There is no guidance about when to use this tool versus alternatives such as invariance_kb_session_create, invariance_kb_session_list_messages, or invariance_session_append_note. The only usage signal is implied by the name and description, with no explicit context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.