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

Annotations only cover the read-only safety profile, yet the description adds substantial behavioral context beyond them: budgets expose budgetVersionId/costMetricId/currency, cost alerts include firingHistory plus a critical warning that the returned `queries` are stored read-only and must not be echoed back to update_alert, and virtual dimensions flag `bqName` as immutable and warn never to derive it from the display `name`. This is exactly the kind of non-obvious caveat structured fields cannot carry.

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?

Purpose and the discriminator are correctly front-loaded, and the per-type prose is organized into labeled sections. However, for a single getter it is very long and folds update/mutation workflows (writing fresh `queries`, projecting rules, update_virtual_dimension_draft) into what is a read operation, which dilutes focus.

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 carries the full burden of describing returns, and it does so thoroughly per type: the `type` discriminator, budget fields, alert firingHistory/scopeId, report config plus run-health and widgets, and virtual-dimension published/draft structure. An agent has enough to interpret and branch on the result.

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 both `id` and `slug`; the baseline is 3. The description adds the budget-specific nuance that `id` may be a parent budget id or a budget version id, but otherwise largely restates what the schema already states.

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 opening sentence gives a specific verb ('Fetch') plus an enumeration of the exact resource types it handles (V2 dashboard, budget, cost alert, report, virtual dimension) by ID, and names the `type` discriminator. This lets an agent distinguish it from sibling getters like get_report_execution or get_dashboard_widget_data without opening the 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?

It explicitly tells the agent to call 'search' (or list tools) first to discover IDs, and names concrete alternatives and follow-ups: get_skill for dashboards/virtual dimensions, get_report_execution for delivery drill-down, and update_alert / update_virtual_dimension_draft / update_dashboard for mutation. This is explicit when-to-use and routing guidance.

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