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

Annotations already establish this as a safe, non-destructive, closed-world read, so the description focuses on the less obvious behavior: what the response contains, that the returned run_input deliberately omits dates, and that a degraded path returns issues instead of a run_input. It does not explain why idempotentHint is false, which is a mildly surprising trait for a read 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?

Front-loaded with purpose and the return contract, then the workflow, then the failure case — a sensible order with no filler. The middle sentence chains several clauses together and would read better as separate steps, but nothing is redundant.

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 two-parameter tool with full schema coverage, an output schema, and read annotations, the description covers the essential gaps: the hand-off to a sibling run tool, the required date input, permitted input adjustment, and the error path. The one omission is how to resolve the issues it reports (e.g. via d8a_prepare_insight_change), which would close the loop.

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%, with both parameters documented including their source tools, so the baseline of 3 applies. The description's only added semantic is that the returned run_input carries no dates, which is about output rather than the two input parameters.

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 resource ('rerun an insight') and goes further by naming the exact return contract (run_tool plus run_input, without dates). It does not distinguish itself from the sibling d8a_get_insight_definition, so an agent must infer which one fetches the definition versus which one prepares a rerun.

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?

Gives an explicit workflow: take run_input, add a date range or preset, optionally add compare, optionally adjust (e.g. add a time_bucket for a trend), then call run_tool. It also covers the blocked case where issues are returned and run_input is absent. Missing only an explicit statement of when to prefer this over d8a_get_insight_definition or running d8a_run_query directly.

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