opencdr_response_outcomes

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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses substantive behavior: failed observations may include partial effects and unknown states require reconciliation before replay, and no historical backfill exists. The statement that fleet forwards only this selected Core read is genuinely useful architectural context not encoded in annotations. The redundant 'no mutation or replay occurs' restates the annotations rather than adding to them.

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?

Short and front-loaded, with the core read scope stated first and constraints following. It is written as clipped sentence fragments with dense jargon ('Fleet forwards only this selected Core read'), which costs some readability. Still, almost every sentence carries information.

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?

There is no output schema, so the description must convey more about return values than it does; the mention of failed/unknown outcomes teases a status vocabulary without explaining the shape of the response. Two of five parameters remain undocumented and the pagination contract (after/limit vs a returned next_after) is only half-explained. Adequate for a read tool, but incomplete for one with no schema documentation.

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?

With 0% schema description coverage the description must carry parameter meaning, and it does so for three of five: after is the previous next_after, limit is bounded to 1..50, and agent_id has mode-dependent semantics. It says nothing about detection_id or attempt_id, so an agent must guess how those two select between the listing mode and the single-attempt history mode. Partial compensation, not full.

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 concrete verb and resource: read retained response/rollback observations, or the immutable history of a single attempt. The two selectable scopes (detection-level listing vs one attempt) are visible, giving an agent a clear picture of what this returns. It stops short of naming any sibling tool to distinguish itself from, leaving that differentiation to the reader.

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 real operational conditions: fleet mode requires agent_id, Core mode leaves it unset, and there is no historical backfill so only retained data is available. However, it never states when to prefer this over adjacent detection/recovery status tools, nor what preconditions must hold before calling. Usage is implied by the mode rules rather than explicitly framed as when-to-use guidance.

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