Escalate to a human when automated self-correction fails: write NEEDS_HUMAN.md with stage, reason, and resolution steps, then return its path.
Self-correction exhausted: write NEEDS_HUMAN.md and return its path.
| Name | Required | Description | Default |
|---|---|---|---|
| stage | Yes | ||
| reason | Yes | ||
| app_dir | Yes | ||
| how_to_resolve | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full behavioral burden. It usefully discloses the side effect (writes a NEEDS_HUMAN.md file) and that it returns a path, but omits whether the run halts, permission/precondition requirements, or what app_dir must contain. It adds some value but is thin for a no-annotation mutation 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?
A single tight sentence with the trigger front-loaded before the action, so nothing is wasted. It is arguably over-sparse given the undocumented parameters, but as a sentence it is well-structured.
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?
An output schema exists, so return values need not be described, and the description covers the core action. But with 4 required params at 0% coverage and no annotations, the definition leaves too much unspecified for an escalation/termination tool.
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% across 4 required parameters (app_dir, stage, reason, how_to_resolve). The description supplies no meaning, format, or examples for any of them, so an agent must guess what 'stage' or 'how_to_resolve' should contain.
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 artifact ('write NEEDS_HUMAN.md and return its path'), plus a trigger condition ('Self-correction exhausted'). It is clearly distinguishable from pipeline/orchestrator siblings by its escalation framing, though it does not name or contrast any sibling explicitly.
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 'Self-correction exhausted' implies when this tool fires, giving an implicit usage condition. However, it never states when NOT to use it or names the alternative (e.g., orchestrator_record_attempt / orchestrator_next_action) that should be preferred while self-correction is still viable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.