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

Annotations already flag destructiveHint=true, but the description goes well beyond that by disclosing the exact per-kind effect: reports/cost alerts/events set archivedAt, virtual dimensions set deletedAt, and dashboards delete the row outright. That distinction between soft-archive and hard-delete is precisely the behavioral detail an agent needs before calling a destructive 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-loads the action and the required parameters, and every line carries information. The three near-identical 'X sets `archivedAt`' sentences are slightly repetitive and could be collapsed, but no sentence is wasted.

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 destructive multi-kind mutation with no output schema and thin schema coverage, the description covers kind selection, per-kind effects, the budget-alert special case, and alternative tools. Nothing an agent needs to invoke it correctly is missing.

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 only 25%, but the description compensates substantially: it explains the resourceKind/alertType coupling, states alertType is the `type` field from list_alerts, and constrains it to costAlert with cost|budget values. This adds meaning the bare enum schema does not convey.

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 (archive) and enumerates the exact resource kinds it accepts, then draws boundaries against siblings (discard_virtual_dimension_draft, delete_tag). An agent can distinguish this from archive_report and the delete/discard tools without opening a schema.

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?

Explicit exclusions with named alternatives are given: virtual-dimension drafts go to discard_virtual_dimension_draft, tags go to delete_tag, no bulk operation, and it must not be used for hard-deleting an alert. It also tells the agent how to route a budget alert through the costAlert kind.

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