Override agent spec activation when strict requirements block deployment, using a durable reason and permission for exceptional cases in the Scenario audit log.
Exceptional activation only. Requires the dedicated permission and a durable reason recorded in the Scenario audit log.
| Name | Required | Description | Default |
|---|---|---|---|
| spec_id | Yes | ||
| idempotency_key | No | ||
| override_reason | Yes | ||
| expected_version | Yes | ||
| override_approver | No |
Changes observed during successful MCP inspections.
v1.3.5Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations the description must carry behavioral disclosure, but it only mentions permission and audit logging. It fails to state what the operation does or its side effects (e.g., changing activation state, idempotency, failure modes). The described constraints are useful but insufficient.
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 text is short and readable, with no fluff, but it is under-specified rather than concise. The first sentence is a fragment, and the second lists requirements without grounding them in the tool's purpose.
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 5-parameter tool with no annotations, no output schema, and a terse description, the agent lacks enough context to call it correctly. The description omits the core action, parameter semantics, expected return, and any error scenarios.
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% and the description names none of the five parameters. It adds no meaning to spec_id, expected_version, override_reason, idempotency_key, or override_approver. The agent still has to guess what each field is for.
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?
Description is a fragment ('Exceptional activation only') that never states the verb or resource; it neither says 'Override activation' nor identifies what is being activated. It is close to a tautology of the name and does not distinguish from siblings like yaaif_agent_spec_adopt or yaaif_agent_spec_publish.
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 vs alternatives. It implies exceptional use and permission needs but never names an alternative or a condition that should redirect to another tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.