Retrieve a shared JSON value by key to access persistent memory across Claude Code and Codex sessions. Use the key to fetch stored data for coordination.
Get a shared JSON value by key.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | ||
| project_id | No | Different project override. Use ONLY when the user explicitly asks for another project by name; otherwise stay in the current scope, even when results are empty. |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false and destructiveHint=true, yet the description frames this as a plain read ('Get a shared JSON value'). Nothing in the text explains the destructive/non-read-only behavior, so the description actively misleads relative to the structured metadata.
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 short, front-loaded sentence with no waste. It is arguably too terse for the behavioral complexity implied by the annotations, but as prose it is efficient.
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?
With no output schema and 50% parameter coverage, the description needed to carry more weight, and it leaves the destructive/non-read-only nature of the operation completely unexplained. An agent could call this believing it is a safe read.
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 50%: project_id carries a strong, self-contained usage constraint, but the required 'key' parameter is undocumented. The description only adds 'by key,' which is already obvious from the schema, so it does not compensate for the gap.
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 ('Get') and resource ('shared JSON value') and identifies the lookup key. It does not explicitly distinguish itself from siblings like kv_list or kv_delete, but the intent is unambiguous.
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?
No when-to-use guidance, no mention of alternatives such as kv_list or kv_delete, and no stated prerequisites. The agent has to infer that this is the single-key read path from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.