aggregate_across_instances

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, so the safety profile is clear. The description adds context about 'fanned out' (parallel execution) and 'combined grand totals', which is beyond annotations but minimal. No contradiction.

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?

The description is very short (one sentence), which is concise but lacks structure. It is front-loaded but does not provide enough detail for its complexity. Every sentence earns its place, but more structure would improve clarity.

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?

Given 5 parameters, 2 required, and 0% schema coverage, the description is incomplete. It does not explain parameters, return values (output schema exists but not provided), or behavior beyond the minimal statement. For a tool with this complexity, it should provide more context.

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 0% (no descriptions in input schema), so the description must compensate. However, it does not explain any of the 5 parameters (model, group_by, domain, measures, instances). It fails to add meaning beyond the schema.

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 states 'Read-only aggregate fanned out across instances with combined grand totals', which clearly identifies the verb (aggregate), resource (across instances), and specific scope (combined grand totals). This distinguishes it from siblings like aggregate_records (single instance) and search_across_instances (search, not aggregate).

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 implies usage for cross-instance aggregation with grand totals but does not explicitly state when to use or avoid it, nor does it name alternatives among siblings. Guidance is implied but not explicit, so it's adequate but not strong.

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