scf_set_reconciliation_actions

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

The description transparently warns that the tool REPLACES the run's planned actions and that partial lists overwrite the rest. However, this contradicts the annotation destructiveHint=false, because overwriting an existing list is a destructive operation. The mixed signal can make an agent underestimate the side effects.

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 dense sentences, no filler. The first sentence states the operation and authorization, and the second front-loads the critical replacement behavior and the action options.

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?

The description covers the core write behavior, authorization, side effects, and decision values, which is sufficient for a tool with a fully documented input schema. It does not mention how this step relates to preview/apply or what the response returns, but those are minor given the sibling names and no output schema.

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 100%, so the schema already documents all parameters and their meanings. The description adds useful emphasis about sending the complete list and the available action values, but it does not meaningfully expand beyond the structured parameter descriptions.

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 names the specific action ('Record decisions'), the resource ('reconciliation run'), and marks it as a write with an admin role. It also states the supported decision values, clearly distinguishing this tool from the many read-only reconciliation siblings like preview, get, and apply.

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 gives clear context: this is the write step for recording reconciliation decisions, requires admin role, and must receive the complete list because prior actions are replaced. It does not explicitly name alternatives or exclude later phases like apply, but the usage context is unambiguous.

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