save_conversationSave a conversation from any LLM client in a normalized format for searching, packaging, or handoff.
Stores a normalized conversation from any LLM client or device so it can be searched, packaged, or handed off.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | ||
| tags | No | ||
| title | Yes | ||
| source | Yes | ||
| lineage | No | ||
| summary | No | ||
| messages | Yes | ||
| metadata | No | ||
| participants | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already state readOnlyHint=false and idempotentHint=false, so the agent knows this is a non-idempotent write. The description adds 'normalized' and purpose but does not disclose side effects like whether it creates a new record, overwrites based on id, or what happens to lineage. For a write tool with zero additional behavioral disclosure, this is a significant gap.
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?
The description is a single, efficient sentence without waste. The main verb is front-loaded. It is concise, though almost too skimpy given the tool's complexity; but as a measure of conciseness and structure, it earns a 4.
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?
Given 9 parameters with nested objects, no output schema, and sparse annotations, the description is far from complete. It lacks any mention of required fields, examples, or semantics of the source object. An agent cannot reliably construct a correct request based solely on this description and the schema.
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 0% and the description mentions none of the 9 parameters. It does not explain what 'title', 'source', 'messages', 'lineage', or 'metadata' mean, nor which are required. With complex nested objects and required fields, the agent has no semantic guidance beyond the raw JSON schema.
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 states a specific verb ('Stores') and resource ('normalized conversation'), plus the intended downstream uses (search, package, hand off). It is clear and distinguishes itself from retrieval/list tools, but it does not explicitly differentiate from the sibling import_conversation, which could also imply storing conversations, so it loses a point.
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 explicit guidance on when to use this tool versus alternatives. It does not say 'use this when' or 'instead of import_conversation', nor does it mention any prerequisites or conditions. The phrase 'from any LLM client or device' hints at breadth but gives no decision criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.