Creates a Markdown or JSON handoff document for the next AI session, preserving context and progress so coding agents can resume work clearly.
AMP: generate the handoff document for the next AI session. format=markdown|json (default: markdown).
| Name | Required | Description | Default |
|---|---|---|---|
| format | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It does not say whether generating a handoff persists anything (writes a file, mutates state) or merely returns text, nor whether the operation is idempotent, what permissions it needs, or how large the output is. For an operation named 'handoff' whose side effects matter, 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?
Two short sentences, front-loaded with the action, with the format/default detail following. No wasted words, though the brevity edges toward under-specification rather than pure efficiency.
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?
No output schema, no annotations, and no description of what the handoff document contains, where it goes, or what the agent receives back. For a tool whose entire value is the artifact it produces, the description leaves the agent unable to predict or verify the result.
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 0%, but the single parameter is an enum whose allowed values are visible in the schema. The description adds real value by specifying the default (markdown), which the schema does not declare. It does not explain any behavioral difference between markdown and json output beyond the surface format.
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: 'generate the handoff document for the next AI session.' The purpose is clear and distinct from siblings like amp_resume or amp_read, though it never explicitly names or contrasts those siblings.
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 'for the next AI session' implies this is called at the end of a session, giving implied usage context. However, there are no explicit when-to-use/when-not rules and no mention of alternatives such as amp_resume, leaving the agent to infer the trigger condition.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.