[neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Recreate an agent from an export_state document.
[neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Recreate an agent from an export_state document.
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | ||
| request_id | No |
Changes observed during successful MCP inspections.
v0.1.13Input schema / properties / request_idAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Request Id"
+}v0.1.11Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It does not state whether this creates a new agent id, overwrites an existing agent, is idempotent, or what permissions/audit effects apply — notable gaps for a mutating reconstruct operation, even though the 'export_state document' framing hints at the input's provenance.
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 actionable sentence with no filler. The bracketed family preamble adds context but slightly delays the core purpose; overall well-sized.
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 no annotations, no output schema, and a 0%-documented nested required parameter, the definition is too thin: an agent cannot tell what happens to an existing agent of the same identity or what a successful import returns.
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 state object is a nested open object. The description only adds that 'state' is a document produced by export_state; it says nothing about required structure/fields, and request_id is entirely undocumented.
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 and resource: 'Recreate an agent from an export_state document.' Combined with the family banner, an agent knows this reconstructs an agent from serialized state. It is clear but does not explicitly distinguish itself from siblings like create_agent or get_agent.
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 phrase 'from an export_state document' implies the intended workflow (the counterpart to export_state), but there is no explicit when-to-use versus create_agent, no preconditions, and no exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.