invariance_run_start

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=false and destructiveHint=false - so the agent knows this is a mutating, non-destructive action that creates a resource. The description adds the key behavioral fact that the run is returned in 'open' status and must be closed later. However, it does not detail the exact lifecycle implications beyond closing, such as what happens if the run is never closed. With annotations covering the mutation profile, a 3 is appropriate.

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 two sentences long with zero fluff. It front-loads the primary action ('Start a new Invariance run') and the container concept, then immediately states the crucial lifecycle requirement (must close it later). Every sentence adds value.

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 creation tool with no output schema, the description clearly defines the run's initial status and the critical close contract. It also references prerequisites (case creation) and inheritance of tenant/end_user. The only minor gap is not explaining that the run is a container for nodes (mentioned) - noting that node writing happens separately (e.g., invariance_node_write) could be beneficial, but the description is otherwise complete for an agent to call it safely.

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?

The input schema provides 100% description coverage for all 5 parameters, with clear descriptions including examples for metadata and the inheritance behavior for tenant_id/end_user_id. The description does not add extra parameter-specific details beyond what the schema already says. Given the high coverage, a baseline of 3 is correct.

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 clearly states the tool starts a new Invariance run, which is a container for a sequence of nodes dropped in the open status. This distinguishes it from related tools like invariance_run_finish and invariance_run_fail, and from the sibling invariance_create_run, by emphasizing lifecycle management.

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 description explicitly states that the returned run is in 'open' status and must be closed later with invariance_run_finish (success) or invariance_run_fail (error). It also mentions that a case must be created first and that tenant_id/end_user_id are normally inherited. This provides clear when-to-use and when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.