Retrieves a JSON value by key from shared persistent memory, enabling cross-session coordination and state access.
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?
No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only says 'Get' without stating that the operation is read-only, has no side effects, or what happens when the key is missing. It does not mention error behavior or return format, which is a significant gap for an unannotated tool.
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 with no filler. It is appropriately sized for a simple get operation and front-loads the core action. Nothing is redundant.
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 tool with no annotations and no output schema, the description is incomplete. It does not state what the tool returns, how to handle missing keys, or the role of the optional project_id override. The agent must infer behavior from the name and schema, which is insufficient for a tool with potential project-scoping nuances.
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% (only project_id has a description). The description adds no parameter-specific information beyond the schema. It does not clarify the semantics of 'key' or explain how project_id affects behavior. Since coverage is not high, the description should compensate but does not.
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 (Get), resource (shared JSON value), and key access mechanism. It clearly differentiates from siblings like kv_list (enumerate) and kv_delete (remove), though it doesn't explicitly name them. It could be slightly more explicit about being a single-value fetch.
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 guidance on when to use this tool versus alternatives like kv_list or kv_set. The context of siblings is present but the description does not reference them or state exclusions. Usage is only implied by the name and description, not explicitly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.